diff --git "a/data/users/hzamani/seedset-hzamani-maple.json" "b/data/users/hzamani/seedset-hzamani-maple.json" --- "a/data/users/hzamani/seedset-hzamani-maple.json" +++ "b/data/users/hzamani/seedset-hzamani-maple.json" @@ -3,15 +3,186 @@ "s2_authorid": "2499986", "papers": [ { - "title": "You can't pick your neighbors, or can you? When and how to rely on retrieval in the $k$NN-LM", + "title": "Pre-Training Multi-Modal Dense Retrievers for Outside-Knowledge Visual Question Answering", "abstract": [ - "Retrieval-enhanced language models (LMs), which condition their predictions on text retrieved from large external datastores, have re-cently shown signi\ufb01cant perplexity improvements compared to standard LMs.", - "One such approach, the k NN-LM, interpolates any existing LM\u2019s predictions with the output of a k nearest neighbors model and requires no additional training.", - "In this paper, we explore the importance of lexical and semantic matching in the context of items retrieved by k NN-LM.", - "We \ufb01nd two trends: (1) the presence of large overlapping n -grams between the datastore and evaluation set plays an important fac-tor in strong performance, even when the datastore is derived from the training data; and (2) the k NN-LM is most bene\ufb01cial when retrieved items have high semantic similarity with the query.", - "Based on our analysis, we de\ufb01ne a new formulation of the k NN-LM that uses retrieval quality to assign the interpolation coef\ufb01cient.", - "We empirically measure the effectiveness of our approach on two English language modeling datasets, Wikitext-103 and PG-19.", - "Our re-formulation of the k NN-LM is bene\ufb01cial in both cases, and leads to nearly 4% improvement in perplexity on the Wikitext-103 test set." + "This paper studies a category of visual question answering tasks, in which accessing external knowledge is necessary for answering the questions.", + "This category is called outside-knowledge visual question answering (OK-VQA).", + "A major step in developing OK-VQA systems is to retrieve relevant documents for the given multi-modal query.", + "Current state-of-the-art asymmetric dense retrieval model for this task uses an architecture with a multi-modal query encoder and a uni-modal document encoder.", + "Such an architecture requires a large amount of training data for effective performance.", + "We propose an automatic data generation pipeline for pre-training passage retrieval models for OK-VQA tasks.", + "The proposed approach leads to 26.9% Precision@5 improvements compared to the current state-of-the-art asymmetric architecture.", + "Additionally, the proposed pre-training approach exhibits a good ability in zero-shot retrieval scenarios." + ] + }, + { + "title": "MarunaBot V2: Towards End-to-End Multi-Modal Task-Oriented Dialogue Systems", + "abstract": [ + "We introduce MarunaBot V2, an advanced Task-Oriented Dialogue System (TODS) primarily aimed at aiding users in cooking and Do-It-Yourself tasks.", + "We utilized large language models (LLMs) for data generation and inference, and implemented hybrid methods for intent classification, retrieval, and question answering, striking a balance between efficiency and performance.", + "A key feature of our system is its multi-modal capabilities.", + "We have incorporated a multi-modal enrichment technique that uses a fine-tuned CLIP model to supplement recipe instructions with pertinent images, a custom Diffusion model for image enhancement and generation, and a method for multi-modal option matching.", + "A unique aspect of our system is its user-centric development approach, facilitated by a custom tool for tracking user interactions and swiftly integrating feedback.", + "Finally, we showcase the promising results of our end-to-end retrieval-augmented LLM taskbot, MarunaChef, and set a promising precedent for future task-oriented dialogue systems." + ] + }, + { + "title": "The 2nd Workshop on Interactive and Scalable Information Retrieval Methods for eCommerce (ISIR-eCom)", + "abstract": [ + "ACM Reference Format: Vachik S. Dave, Linsey Pang, Xiquan Cui, Lingfei Wu, Hamed Zamani, and George Karypis.", + "2023.", + "The 2nd Workshop on Interactive and Scalable Information Retrieval Methods for eCommerce (ISIR-eCom).", + "In Companion Proceedings of the ACM Web Conference 2023 (WWW \u201923 Companion), April 30\u2013May 04, 2023, Austin, TX, USA.", + "ACM, New York, NY, USA, 4 pages.", + "https://doi.org/10.1145/3543873.3589753" + ] + }, + { + "title": "LaMP: When Large Language Models Meet Personalization", + "abstract": [ + "This paper highlights the importance of personalization in large language models and introduces the LaMP benchmark -- a novel benchmark for training and evaluating language models for producing personalized outputs.", + "LaMP offers a comprehensive evaluation framework with diverse language tasks and multiple entries for each user profile.", + "It consists of seven personalized tasks, spanning three text classification and four text generation tasks.", + "We additionally propose two retrieval augmentation approaches that retrieve personal items from each user profile for personalizing language model outputs.", + "To this aim, we study various retrieval models, including term matching, semantic matching, and time-aware methods.", + "Extensive experiments on LaMP for zero-shot and fine-tuned language models demonstrate the efficacy of the proposed retrieval augmentation approach and highlight the impact of personalization in various natural language tasks." + ] + }, + { + "title": "A Personalized Dense Retrieval Framework for Unified Information Access", + "abstract": [ + "Developing a universal model that can efficiently and effectively respond to a wide range of information access requests-from retrieval to recommendation to question answering---has been a long-lasting goal in the information retrieval community.", + "This paper argues that the flexibility, efficiency, and effectiveness brought by the recent development in dense retrieval and approximate nearest neighbor search have smoothed the path towards achieving this goal.", + "We develop a generic and extensible dense retrieval framework, called framework, that can handle a wide range of (personalized) information access requests, such as keyword search, query by example, and complementary item recommendation.", + "Our proposed approach extends the capabilities of dense retrieval models for ad-hoc retrieval tasks by incorporating user-specific preferences through the development of a personalized attentive network.", + "This allows for a more tailored and accurate personalized information access experience.", + "Our experiments on real-world e-commerce data suggest the feasibility of developing universal information access models by demonstrating significant improvements even compared to competitive baselines specifically developed for each of these individual information access tasks.", + "This work opens up a number of fundamental research directions for future exploration." + ] + }, + { + "title": "Multivariate Representation Learning for Information Retrieval", + "abstract": [ + "Dense retrieval models use bi-encoder network architectures for learning query and document representations.", + "These representations are often in the form of a vector representation and their similarities are often computed using the dot product function.", + "In this paper, we propose a new representation learning framework for dense retrieval.", + "Instead of learning a vector for each query and document, our framework learns a multivariate distribution and uses negative multivariate KL divergence to compute the similarity between distributions.", + "For simplicity and efficiency reasons, we assume that the distributions are multivariate normals and then train large language models to produce mean and variance vectors for these distributions.", + "We provide a theoretical foundation for the proposed framework and show that it can be seamlessly integrated into the existing approximate nearest neighbor algorithms to perform retrieval efficiently.", + "We conduct an extensive suite of experiments on a wide range of datasets, and demonstrate significant improvements compared to competitive dense retrieval models." + ] + }, + { + "title": "Generalized Weak Supervision for Neural Information Retrieval", + "abstract": [ + "Neural ranking models (NRMs) have demonstrated effective performance in several information retrieval (IR) tasks.", + "However, training NRMs often requires large-scale training data, which is difficult and expensive to obtain.", + "To address this issue, one can train NRMs via weak supervision, where a large dataset is automatically generated using an existing ranking model (called the weak labeler) for training NRMs.", + "Weakly supervised NRMs can generalize from the observed data and significantly outperform the weak labeler.", + "This paper generalizes this idea through an iterative re-labeling process, demonstrating that weakly supervised models can iteratively play the role of weak labeler and significantly improve ranking performance without using manually labeled data.", + "The proposed Generalized Weak Supervision (GWS) solution is generic and orthogonal to the ranking model architecture.", + "This paper offers four implementations of GWS: self-labeling, cross-labeling, joint cross- and self-labeling, and greedy multi-labeling.", + "GWS also benefits from a query importance weighting mechanism based on query performance prediction methods to reduce noise in the generated training data.", + "We further draw a theoretical connection between self-labeling and Expectation-Maximization.", + "Our experiments on two passage retrieval benchmarks suggest that all implementations of GWS lead to substantial improvements compared to weak supervision in all cases." + ] + }, + { + "title": "Large Language Model Augmented Narrative Driven Recommendations", + "abstract": [ + "Narrative-driven recommendation (NDR) presents an information access problem where users solicit recommendations with verbose descriptions of their preferences and context, for example, travelers soliciting recommendations for points of interest while describing their likes/dislikes and travel circumstances.", + "These requests are increasingly important with the rise of natural language-based conversational interfaces for search and recommendation systems.", + "However, NDR lacks abundant training data for models, and current platforms commonly do not support these requests.", + "Fortunately, classical user-item interaction datasets contain rich textual data, e.g., reviews, which often describe user preferences and context \u2013 this may be used to bootstrap training for NDR models.", + "In this work, we explore using large language models (LLMs) for data augmentation to train NDR models.", + "We use LLMs for authoring synthetic narrative queries from user-item interactions with few-shot prompting and train retrieval models for NDR on synthetic queries and user-item interaction data.", + "Our experiments demonstrate that this is an effective strategy for training small-parameter retrieval models that outperform other retrieval and LLM baselines for narrative-driven recommendation." + ] + }, + { + "title": "Gonads Exposure to Scattered Radiation and Associated Second Cancer Risk from Pelvic Radiotherapy", + "abstract": [ + "Purpose: The purpose of this study was to evaluate the risk of gonad cancer induction in adults with pelvic cancer (bladder, rectum, endometriosis) after radiation therapy.", + "\nMaterials and Methods: In two fractions of radiotherapy, Thermo Luminescence Dosimeters (TLDs) measured the peripheral dose to the testis and ovary.", + "With 3D planning, all patients received a 45 Gy total dose in four fields in the prone position.", + "Researchers investigated the doses produced by linear accelerators operating at 18 MeV. \nResults: The mean Excess Relative Risk (ERR) was measured based on the BEIR IIV models.", + "Right pelvic radiotherapy of men was 0.795 \u00b1 0.168 and 0.675 \u00b1 0.134, and for women was 1.015 \u00b1 0.561 and 0.884 \u00b1 0.468 after 5 and 10 years of treatment, respectively.", + "Left pelvic radiotherapy was 0.855 \u00b1 0.172, 0.725 \u00b1 0.138 for men and 0.880 \u00b1 0.464, 0.722 \u00b1 0.342 for women respectively (95% confidence interval).", + "These values for women were higher (p < 0.05).", + "\nConclusion: Estimating the second cancer risk of untargeted organs is crucial in radiotherapy.", + "The out-of-field doses can be minimized by using a linear accelerator with a single energy mode and proper shields." + ] + }, + { + "title": "Tutorials at The Web Conference 2023", + "abstract": [ + "This paper summarizes the content of the 28 tutorials that have been given at The Web Conference 2023." + ] + }, + { + "title": "Soft Prompt Decoding for Multilingual Dense Retrieval", + "abstract": [ + "In this work, we explore a Multilingual Information Retrieval (MLIR) task, where the collection includes documents in multiple languages.", + "We demonstrate that applying state-of-the-art approaches developed for cross-lingual information retrieval to MLIR tasks leads to sub-optimal performance.", + "This is due to the heterogeneous and imbalanced nature of multilingual collections -- some languages are better represented in the collection and some benefit from large-scale training data.", + "To address this issue, we present KD-SPD, a novel soft prompt decoding approach for MLIR that implicitly \"translates'' the representation of documents in different languages into the same embedding space.", + "To address the challenges of data scarcity and imbalance, we introduce a knowledge distillation strategy.", + "The teacher model is trained on rich English retrieval data, and by leveraging bi-text data, our distillation framework transfers its retrieval knowledge to the multilingual document encoder.", + "Therefore, our approach does not require any multilingual retrieval training data.", + "Extensive experiments on three MLIR datasets with a total of 15 languages demonstrate that KD-SPD significantly outperforms competitive baselines in all cases.", + "We conduct extensive analyses to show that our method has less language bias and better zero-shot transfer ability towards new languages." + ] + }, + { + "title": "Editable User Profiles for Controllable Text Recommendations", + "abstract": [ + "Methods for making high-quality recommendations often rely on learning latent representations from interaction data.", + "These methods, while performant, do not provide ready mechanisms for users to control the recommendation they receive.", + "Our work tackles this problem by proposing LACE, a novel concept value bottleneck model for controllable text recommendations.", + "LACE represents each user with a succinct set of human-readable concepts through retrieval given user-interacted documents and learns personalized representations of the concepts based on user documents.", + "This concept based user profile is then leveraged to make recommendations.", + "The design of our model affords control over the recommendations through a number of intuitive interactions with a transparent user profile.", + "We first establish the quality of recommendations obtained from LACE in an offline evaluation on three recommendation tasks spanning six datasets in warm-start, cold-start, and zero-shot setups.", + "Next, we validate the controllability of LACE under simulated user interactions.", + "Finally, we implement LACE in an interactive controllable recommender system and conduct a user study to demonstrate that users are able to improve the quality of recommendations they receive through interactions with an editable user profile." + ] + }, + { + "title": "SIGIR 2023 Workshop on Retrieval Enhanced Machine Learning (REML @ SIGIR 2023)", + "abstract": [ + "Most machine learning models are designed to be self-contained and encode both \"knowledge\" and \"reasoning\" in their parameters.", + "However, such models cannot perform effectively for tasks that require knowledge grounding and tasks that deal with non-stationary data, such as news and social media.", + "Besides, these models often require huge number of parameters to encode all the required knowledge.", + "These issues can be addressed via augmentation with a retrieval model.", + "This category of machine learning models, which is called Retrieval-enhanced machine learning (REML), has recently attracted considerable attention in multiple research communities.", + "For instance, REML models have been studied in the context of open-domain question answering, fact verification, and dialogue systems and also in the context of generalization through memorization in language models and memory networks.", + "We believe that the information retrieval community can significantly contribute to this growing research area by designing, implementing, analyzing, and evaluating various aspects of retrieval models with applications to REML tasks.", + "The goal of this full-day hybrid workshop is to bring together researchers from industry and academia to discuss various aspects of retrieval-enhanced machine learning, including effectiveness, efficiency, and robustness of these models in addition to their impact on real-world applications." + ] + }, + { + "title": "A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering", + "abstract": [ + "Knowledge-Intensive Visual Question Answering (KI-VQA) refers to answering a question about an image whose answer does not lie in the image.", + "This paper presents a new pipeline for KI-VQA tasks, consisting of a retriever and a reader.", + "First, we introduce DEDR, a symmetric dual encoding dense retrieval framework in which documents and queries are encoded into a shared embedding space using uni-modal (textual) and multi-modal encoders.", + "We introduce an iterative knowledge distillation approach that bridges the gap between the representation spaces in these two encoders.", + "Extensive evaluation on two well-established KI-VQA datasets, i.e., OK-VQA and FVQA, suggests that DEDR outperforms state-of-the-art baselines by 11.6% and 30.9% on OK-VQA and FVQA, respectively.", + "Utilizing the passages retrieved by DEDR, we further introduce MM-FiD, an encoder-decoder multi-modal fusion-in-decoder model, for generating a textual answer for KI-VQA tasks.", + "MM-FiD encodes the question, the image, and each retrieved passage separately and uses all passages jointly in its decoder.", + "Compared to competitive baselines in the literature, this approach leads to 5.5% and 8.5% improvements in terms of question answering accuracy on OK-VQA and FVQA, respectively." + ] + }, + { + "title": "Learning List-Level Domain-Invariant Representations for Ranking", + "abstract": [ + "Domain adaptation aims to transfer the knowledge learned on (data-rich) source domains to (low-resource) target domains, and a popular method is invariant representation learning, which matches and aligns the data distributions on the feature space.", + "Although this method is studied extensively and applied on classification and regression problems, its adoption on ranking problems is sporadic, and the few existing implementations lack theoretical justifications.", + "This paper revisits invariant representation learning for ranking.", + "Upon reviewing prior work, we found that they implement what we call item-level alignment, which aligns the distributions of the items being ranked from all lists in aggregate but ignores their list structure.", + "However, the list structure should be leveraged, because it is intrinsic to ranking problems where the data and the metrics are defined and computed on lists, not the items by themselves.", + "To close this discrepancy, we propose list-level alignment -- learning domain-invariant representations at the higher level of lists.", + "The benefits are twofold: it leads to the first domain adaptation generalization bound for ranking, in turn providing theoretical support for the proposed method, and it achieves better empirical transfer performance for unsupervised domain adaptation on ranking tasks, including passage reranking." ] }, { @@ -77,10 +248,10 @@ "abstract": [ "This paper studies multi-task training of retrieval-augmented generation models for knowledge-intensive tasks.", "We propose to clean the training set by utilizing a distinct property of knowledge-intensive generation: The connection of query-answer pairs to items in the knowledge base.", - "We \ufb01lter training examples via a threshold of con\ufb01dence on the relevance labels, whether a pair is answerable by the knowledge base or not.", + "We filter training examples via a threshold of confidence on the relevance labels, whether a pair is answerable by the knowledge base or not.", "We train a single Fusion-in-Decoder (FiD) generator on seven combined tasks of the KILT benchmark.", - "The experimental results suggest that our simple yet effective approach substantially improves competitive baselines on two strongly imbalanced tasks; and shows either smaller improvements or no signi\ufb01cant regression on the remaining tasks.", - "Furthermore, we demonstrate our multi-task training with relevance label sampling scales well with increased model capacity and achieves state-of-the-art results in \ufb01ve out of seven KILT tasks." + "The experimental results suggest that our simple yet effective approach substantially improves competitive baselines on two strongly imbalanced tasks; and shows either smaller improvements or no significant regression on the remaining tasks.", + "Furthermore, we demonstrate our multi-task training with relevance label sampling scales well with increased model capacity and achieves state-of-the-art results in five out of seven KILT tasks." ] }, { @@ -131,8 +302,6 @@ "The guardrails check for failures on certain query characteristics and novel failure types that are only possible in dense retrieval systems.", "We demonstrate our decision framework on a Web ranking scenario.", "In that scenario, state-of-the-art DR models have surprisingly strong results, not only on average performance but passing an extensive set of guardrail tests, showing robustness on different query characteristics, lexical matching, generalization, and number of regressions.", - "DR with approximate nearest neighbor search has comparable low query latency to term-based systems.", - "The main reason to reject current DR models in this scenario is the cost of vectorization, which is much higher than the cost of building a traditional index.", "It is impossible to predict whether DR will become ubiquitous in the future, but one way this is possible is through repeated applications of decision processes such as the one presented here." ] }, @@ -174,6 +343,16 @@ "Therefore, the risks and benefits of each method should be considered before their prescription." ] }, + { + "title": "Towards Mixed-Initiative Conversational Information Seeking", + "abstract": [ + "While conversational information seeking has roots in early information retrieval research, recent advances in automatic speech recognition and conversational agents as well as popularity of devices with limited bandwidth interfaces have led to increasing interest in this area.", + "An ideal conversational information seeking system requires to go beyond the typical \u201cquery-response\u201d paradigm by supporting mixed-initiative interactions.", + "In this talk, I will review the recent efforts on developing mixed-initiative conversational information seeking systems and draw connections with early work on interactive information retrieval.", + "I will describe methods for generating and evaluating clarifying questions in response to information seeking requests.", + "I will further highlight the connections between conversational search and recommendation, and finish with a discussion on the next steps that require significant progress in the context of mixed-initiative conversational information seeking." + ] + }, { "title": "Estimating the risks of exposure-induced death associated with common computed tomography procedures", "abstract": [ @@ -199,6 +378,320 @@ "The REML research agenda lays a foundation for a new style of information access research and paves a path towards advancing machine learning and artificial intelligence." ] }, + { + "title": "You can't pick your neighbors, or can you? When and how to rely on retrieval in the kNN-LM", + "abstract": [ + "Retrieval-enhanced language models (LMs), which condition their predictions on text retrieved from large external datastores, have recently shown significant perplexity improvements compared to standard LMs.", + "One such approach, the $k$NN-LM, interpolates any existing LM's predictions with the output of a $k$-nearest neighbors model and requires no additional training.", + "In this paper, we explore the importance of lexical and semantic matching in the context of items retrieved by $k$NN-LM.", + "We find two trends: (1) the presence of large overlapping $n$-grams between the datastore and evaluation set plays an important factor in strong performance, even when the datastore is derived from the training data; and (2) the $k$NN-LM is most beneficial when retrieved items have high semantic similarity with the query.", + "Based on our analysis, we define a new formulation of the $k$NN-LM that uses retrieval quality to assign the interpolation coefficient.", + "We empirically measure the effectiveness of our approach on two English language modeling datasets, Wikitext-103 and PG-19.", + "Our re-formulation of the $k$NN-LM is beneficial in both cases, and leads to nearly 4% improvement in perplexity on the Wikitext-103 test set." + ] + }, + { + "title": "FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation", + "abstract": [ + "Retrieval-augmented generation models offer many benefits over standalone language models: besides a textual answer to a given query they provide provenance items retrieved from an updateable knowledge base.", + "However, they are also more complex systems and need to handle long inputs.", + "In this work, we introduce FiD-Light to strongly increase the efficiency of the state-of-the-art retrieval-augmented FiD model, while maintaining the same level of effectiveness.", + "Our FiD-Light model constrains the information flow from the encoder (which encodes passages separately) to the decoder (using concatenated encoded representations).", + "Furthermore, we adapt FiD-Light with re-ranking capabilities through textual source pointers, to improve the top-ranked provenance precision.", + "Our experiments on a diverse set of seven knowledge intensive tasks (KILT) show FiD-Light consistently improves the Pareto frontier between query latency and effectiveness.", + "FiD-Light with source pointing sets substantial new state-of-the-art results on six KILT tasks for combined text generation and provenance retrieval evaluation, while maintaining high efficiency." + ] + }, + { + "title": "Generalizing Discriminative Retrieval Models using Generative Tasks", + "abstract": [ + "Information Retrieval has a long history of applying either discriminative or generative modeling to retrieval and ranking tasks.", + "Recent developments in transformer architectures and multi-task learning techniques have dramatically improved our ability to train effective neural models capable of resolving a wide variety of tasks using either of these paradigms.", + "In this paper, we propose a novel multi-task learning approach which can be used to produce more effective neural ranking models.", + "The key idea is to improve the quality of the underlying transformer model by cross-training a retrieval task and one or more complementary language generation tasks.", + "By targeting the training on the encoding layer in the transformer architecture, our experimental results show that the proposed multi-task learning approach consistently improves retrieval effectiveness on the targeted collection and can easily be re-targeted to new ranking tasks.", + "We provide an in-depth analysis showing how multi-task learning modifies model behaviors, resulting in more general models." + ] + }, + { + "title": "Explaining Documents' Relevance to Search Queries", + "abstract": [ + "We present GenEx, a generative model to explain search results to users beyond just showing matches between query and document words.", + "Adding GenEx explanations to search results greatly impacts user satisfaction and search performance.", + "Search engines mostly provide document titles, URLs, and snippets for each result.", + "Existing model-agnostic explanation methods similarly focus on word matching or content-based features.", + "However, a recent user study shows that word matching features are quite obvious to users and thus of slight value.", + "GenEx explains a search result by providing a terse description for the query aspect covered by that result.", + "We cast the task as a sequence transduction problem and propose a novel model based on the Transformer architecture.", + "To represent documents with respect to the given queries and yet not generate the queries themselves as explanations, two query-attention layers and masked-query decoding are added to the Transformer architecture.", + "The model is trained without using any human-generated explanations.", + "Training data are instead automatically constructed to ensure a tolerable noise level and a generalizable learned model.", + "Experimental evaluation shows that our explanation models significantly outperform the baseline models.", + "Evaluation through user studies also demonstrates that our explanation model generates short yet useful explanations." + ] + }, + { + "title": "Estimation of Diagnostic Reference Levels and Achievable Doses for Pediatric Patients in Common Computed Tomography Examinations: A Multi-Center Study.", + "abstract": [ + "This study was conducted to determine first local diagnostic reference levels (DRLs) and achievable doses (ADs) for pediatric patients during the most common computed tomography (CT) procedures in Yazd province.", + "The DRL was obtained based on volume CT dose index (CTDIvol) and dose length product (DLP) for four various age groups of children.", + "Data were collected from the most commonly performed pediatric CT scans, including abdomen-pelvis, chest, brain and sinus examinations, at six high-loaded institutes.", + "The patients' data (766 no.) in terms of CTDIvol and DLP were obtained from four age groups: \u22641-, 1-5-, 5-10- and 10-15-y-old.", + "The 75th percentiles of CTDIvol and DLP were considered as DRL values and the 50th percentiles were described as ADs for those parameters.", + "Consequently, the acquired DRLs were compared with other national and international published values.", + "The DRLs in terms of CTDIvol for abdomen-pelvis, chest, brain and sinus examinations were 3, 8, 9 and 10 mGy; 4, 5, 5 and 5 mGy; 25, 28, 29 and 38 mGy; and 23, 24, 26 and 27 mGy for four different age groups of \u22641-, 1-5-, 5-10- and 10-15-y-old, respectively.", + "The DRL values in terms of DLP were 75, 302, 321 and 342 mGy.cm; 109, 112, 135 and 170 mGy.cm, 352, 355, 360 and 481 mGy.cm; and 206, 211, 228 and 245 mGy.cm, respectively, for the mentioned age groups.", + "In this study, the DRL and AD values in the brain examination were greater among the other studied regions.", + "The DRL plays a critical role in the optimization of radiation doses delivered to patients and in improving their protection.", + "This study provides the local DRLs and ADs for the most common pediatric CT scanning in Yazd province to create optimum situation for the clinical practice." + ] + }, + { + "title": "Estimating the radiation surface dose and measuring the dose area product to provide the diagnostic reference level in panoramic radiography", + "abstract": [ + "Background: Panoramic radiography is one of the common dental imaging procedures using ionizing radiation.", + "It is necessary to control the level of exposure and use the optimized levels.", + "So, the current work aimed to estimate the surface absorbed doses of critical organ regions, namely thyroid and parotid glands.", + "Moreover, dose area product (DAP) values were measured and a local DRL was then established for panoramic radiography.", + "Materials and Methods: The data from 201 patients including 141 adults and 60 children (5-10 years) were used for this cross-sectional study.", + "Seven panoramic radiography systems were selected from 6 radiology clinics in Yazd province.", + "For each patient, 12 thermoluminescence dosimeters (TLD GR-200) were used to obtain the surface absorbed dose in both the thyroid and parotid gland regions.", + "The DRL values were calculated using DAP values in terms of the ICRP recommendation.", + "Results: The mean and standard deviation (SD) of thyroid and parotid glands\u2019 surface absorbed doses were equal to 60.6\u00b13.7 and 290\u00b112.4 \u03bcGy in the adult group, respectively.", + "In the children group, these values were 40.7\u00b12 and 189.3\u00b111.5 \u03bcGy, respectively.", + "Moreover, the local DRL values were obtained as 99.7 and 73.4 mGy.cm for the adults and children groups, respectively.", + "Conclusion: The higher surface absorbed dose values in the adult group can be related to the use of higher radiation parameters.", + "The local DRL proposed for the adult and pediatric groups in the current study was relatively lower than those established by other reports, which seemed acceptable for panoramic radiography in Yazd," + ] + }, + { + "title": "Context-aware Target Apps Selection and Recommendation for Enhancing Personal Mobile Assistants", + "abstract": [ + "Users install many apps on their smartphones, raising issues related to information overload for users and resource management for devices.", + "Moreover, the recent increase in the use of personal assistants has made mobile devices even more pervasive in users\u2019 lives.", + "This article addresses two research problems that are vital for developing effective personal mobile assistants: target apps selection and recommendation.", + "The former is the key component of a unified mobile search system: a system that addresses the users\u2019 information needs for all the apps installed on their devices with a unified mode of access.", + "The latter, instead, predicts the next apps that the users would want to launch.", + "Here we focus on context-aware models to leverage the rich contextual information available to mobile devices.", + "We design an in situ study to collect thousands of mobile queries enriched with mobile sensor data (now publicly available for research purposes).", + "With the aid of this dataset, we study the user behavior in the context of these tasks and propose a family of context-aware neural models that take into account the sequential, temporal, and personal behavior of users.", + "We study several state-of-the-art models and show that the proposed models significantly outperform the baselines." + ] + }, + { + "title": "LearningMultiple Intent Representations for SearchQueries", + "abstract": [ + "Representation learning has always played an important role in information retrieval (IR) systems.", + "Most retrieval models, including recent neural approaches, use representations to calculate similarities between queries and documents to find relevant information from a corpus.", + "Recent models use large-scale pre-trained language models for query representation.", + "The typical use of these models, however, has a major limitation in that they generate only a single representation for a query,whichmayhavemultiple intents or facets.", + "The focus of this paper is to address this limitation by considering neural models that support multiple intent representations for each query.", + "Specifically, we propose the NMIR (Neural Multiple Intent Representations) model that can generate semantically different query intents and their appropriate representations.", + "We evaluate our model on query facet generation using a large-scale dataset of real user queries sampled from the Bing search logs.", + "We also provide an extrinsic evaluation of the proposed model using a clarifying question selection task.", + "The results show that NMIR significantly outperforms competitive baselines.", + "ACMReference Format: Helia Hashemi, Hamed Zamani, andW. Bruce Croft.", + "2021.", + "LearningMultiple Intent Representations for Search Queries.", + "In Proceedings of the 30th ACM International Conference on Information and Knowledge Management (CIKM \u201921), November 1\u20135, 2021, Virtual Event, QLD, Australia.", + "ACM, New York, NY, USA, 11 pages.", + "https://doi.org/10.1145/3459637.3482445" + ] + }, + { + "title": "Improving Transformer-Kernel Ranking Model Using Conformer and Query Term Independence", + "abstract": [ + "The Transformer-Kernel (TK) model has demonstrated strong reranking performance on the TREC Deep Learning benchmark---and can be considered to be an efficient (but slightly less effective) alternative to other Transformer-based architectures that employ (i) large-scale pretraining (high training cost), (ii) joint encoding of query and document (high inference cost), and (iii) larger number of Transformer layers (both high training and high inference costs).", + "Since, a variant of the TK model---called TKL---has been developed that incorporates local self-attention to efficiently process longer input sequences in the context of document ranking.", + "In this work, we propose a novel Conformer layer as an alternative approach to scale TK to longer input sequences.", + "Furthermore, we incorporate query term independence and explicit term matching to extend the model to the full retrieval setting.", + "We benchmark our models under the strictly blind evaluation setting of the TREC 2020 Deep Learning track and find that our proposed architecture changes lead to improved retrieval quality over TKL.", + "Our best model also outperforms all non-neural runs (\"trad\") and two-thirds of the pretrained Transformer-based runs (\"nnlm\") on NDCG@10." + ] + }, + { + "title": "CSFCube - A Test Collection of Computer Science Research Articles for Faceted Query by Example", + "abstract": [ + "Query by Example is a well-known information retrieval task in which a document is chosen by the user as the search query and the goal is to retrieve relevant documents from a large collection.", + "However, a document often covers multiple aspects of a topic.", + "To address this scenario we introduce the task of faceted Query by Example in which users can also specify a finer grained aspect in addition to the input query document.", + "We focus on the application of this task in scientific literature search.", + "We envision models which are able to retrieve scientific papers analogous to a query scientific paper along specifically chosen rhetorical structure elements as one solution to this problem.", + "In this work, the rhetorical structure elements, which we refer to as facets, indicate objectives, methods, or results of a scientific paper.", + "We introduce and describe an expert annotated test collection to evaluate models trained to perform this task.", + "Our test collection consists of a diverse set of 50 query documents in English, drawn from computational linguistics and machine learning venues.", + "We carefully follow the annotation guideline used by TREC for depth-k pooling (k = 100 or 250) and the resulting data collection consists of graded relevance scores with high annotation agreement.", + "State of the art models evaluated on our dataset show a significant gap to be closed in further work.", + "Our dataset may be accessed here: https://github.com/iesl/CSFCube" + ] + }, + { + "title": "Effect of feeding fermented and non-fermented palm kernel cake on the performance of broiler chickens: a review", + "abstract": [ + "SUMMARY Palm kernel cake (PKC) is a by-product of oil extraction from palm fruits and has been included in poultry diets as an alternative to soybean meal and yellow corn.", + "Due to its high content of fibre, coarse texture and gritty appearance, the use of PKC in poultry nutrition is limited.", + "In order to increase the nutritive value of PKC, there is a tendency nowadays to create solid state fermentation (SSF) by using cellulolytic microbes.", + "This paper reviews the impact of feeding fermented and non-fermented PKC on the performance of broiler chickens.", + "Recent studies have reported that SSF by cellulolytic microorganisms improved the nutritive value of PKC.", + "The nutrient digestibility has been increased significantly in PKC fermented using Paenibacillus polymyxya ATCC 842 or Weisella confusa SR-17b.", + "The availability of valine, histidine, methionine and arginine was 70.42%, 71.50%, 71.92% and 81.15%, respectively, in PKC fermented using P. polymyxa ATCC 842.", + "The digestibility of crude protein (CP) increased by 61.83% and 59.90% in PKC fermented using P. polymyxya ATCC 842 or W. confusa SR-17b, respectively.", + "In addition, body weight gain (BWG) and feed conversion ratio (FCR) improved significantly in broilers fed 15% fermented PKC compared to those fed 15% non-fermented PKC (2000.43 g versus 1823.23 g and 1.75 versus 1.91, respectively).", + "The intestinal Enterobacteriaceae decreased (4.03 CFU/g) and lactic acid bacteria increased (5.56 CFU/g) in birds fed 15% PKC fermented by P. polymyxa ATCC 842.", + "Therefore, fermented PKC can be included in a broiler diet up to 15%, replacing part of soybean and yellow corn in the diet, leading to a decrease in the overall cost of poultry feeding." + ] + }, + { + "title": "Conversational Search and Recommendation: Introduction to the Special Issue", + "abstract": [ + "While conversational search and recommendation has roots in early Information Retrieval (IR) research, the recent advances in automatic voice recognition and conversational agents have created increasing interest in this area.", + "This topic was recognized as an emerging research area in the Third Strategic Workshop on Information Retrieval in Lorne (SWIRL 2018) [Culpepper et al. 2018].", + "Conversational search and recommendation systems consist of multiple components, from user modeling to conversational understanding to query modeling to result presentation.", + "In recent years, the IR and related communities have witnessed a number of major contributions to the field of conversational search and recommendation.", + "They include but are not limited to conversational search conceptualization (e.g., Azzopardi et al. [2018], Deldjoo et al. [2021], and Radlinski and Craswell [2017]), effective conversational query re-writing (e.g., Yu et al. [2020]), generating and selecting clarifying questions (e.g., Zamani et al. [2020a, c]), conversational preference elicitation (e.g., Radlinski et al. [2019] and Zhang et al. [2018]), and understanding user interactions with spoken conversational systems (e.g., Trippas et al. [2018, 2020]).", + "The growing body of work in this area has been supplemented by an increasing number of recent seminars (e.g., Anand et al. [2020]), workshops (e.g., Arguello et al. [2018], Burtsev et al. [2017], Chuklin et al. [2018], and" + ] + }, + { + "title": "Towards System-Initiative Conversational Information Seeking", + "abstract": [ + "Presently, most conversational information seeking systems function in a passive manner, i.e., user-initiative engagement.", + "Through this work, we aim to discuss the importance of developing conversational information seeking systems capable of system-initiative interactions.", + "We further discuss various aspects of such interactions in CIS systems and introduce a taxonomy of system-initiative interactions based on three orthogonal dimensions: initiation moment (when to initiative a conversation), initiation purpose (why to initiate a conversation), and initiation means (how to initiate a conversation).", + "This taxonomy enables us to propose a generic pipeline for system-initiative conversations, consisting of three major steps associated with the three dimensions highlighted in the taxonomy.", + "We further delineate the technical and evaluation challenges that the design and implementation of each component may encounter, and provide possible solutions.", + "We finally point out potential broader impacts of system-initiative interactions in CIS systems." + ] + }, + { + "title": "Current Challenges and Future Directions in Podcast Information Access", + "abstract": [ + "Podcasts are spoken documents across a wide-range of genres and styles, with growing listenership across the world, and a rapidly lowering barrier to entry for both listeners and creators.", + "The great strides in search and recommendation in research and industry have yet to see impact in the podcast space, where recommendations are still largely driven by word of mouth.", + "In this perspective paper, we highlight the many differences between podcasts and other media, and discuss our perspective on challenges and future research directions in the domain of podcast information access." + ] + }, + { + "title": "Evaluation of Conventional Radiographic Systems in Shahid Sadoughi University of Medical Sciences: A Multi-Centric Quality Control Study", + "abstract": [ + "Introduction: Generally, the benefits of radiological examinations performed on individuals far outweigh their risks; however, this is not true when the radiographic system fails to work properly.", + "Therefore, to avoid such errors, it is crucial to frequently perform Quality Control (QC) checks in an imaging facility.", + "\nMaterial and Methods: A total of 11 highly-referred centers out of 62 radiology rooms located in Yazd province were included in this investigation, and QC tests comprising light/radiation field alignment, the accuracy of kilovoltage and exposure time, reproducibility of kilovoltage, exposure time, and output, and linearity of output against exposure time and milliamperage were performed for each equipment.", + "The light and radiation field alignment test were carried out by a quantitative assessment of digital images of a collimator template (PTW-Freiburg, Germany).", + "The measurements were made by a Barracuda package and a Multi-Purpose Detector (MPD).", + "\nResults: In terms of the light/radiation field alignment check, unit A failed to satisfy the national regulations.", + "Concerning the timer reproducibility, 64% of the units failed to meet the criteria.", + "All of the devices passed the rest of the checks satisfactorily.", + "\nConclusion: This study uncovered that most of the radiology rooms in Yazd province are in an adequate situation based on the QC tests; however, more than half of the units do not satisfy the timer reproducibility criteria.", + "Hence, more supervision needs to be directed at these systems by qualified radiation safety officers who are responsible for the protection of the population against ionization radiation." + ] + }, + { + "title": "Tip of the Tongue Known-Item Retrieval: A Case Study in Movie Identification", + "abstract": [ + "While current information retrieval systems are effective for known-item retrieval where the searcher provides a precise name or identifier for the item being sought, systems tend to be much less effective for cases where the searcher is unable to express a precise name or identifier.", + "We refer to this as tip of the tongue (TOT) known-item retrieval, named after the cognitive state of not being able to retrieve an item from memory.", + "Using movie search as a case study, we explore the characteristics of questions posed by searchers in TOT states in a community question answering website.", + "We analyze how searchers express their information needs during TOT states in the movie domain.", + "Specifically, what information do searchers remember about the item being sought and how do they convey this information?", + "Our results suggest that searchers use a combination of information about: (1) the content of the item sought, (2) the context in which they previously engaged with the item, and (3) previous attempts to find the item using other resources (e.g., search engines).", + "Additionally, searchers convey information by sometimes expressing uncertainty (i.e., hedging), opinions, emotions, and by performing relative (vs. absolute) comparisons with attributes of the item.", + "As a result of our analysis, we believe that searchers in TOT states may require specialized query understanding methods or document representations.", + "Finally, our preliminary retrieval experiments show the impact of each information type presented in information requests on retrieval performance." + ] + }, + { + "title": "Learning Robust Dense Retrieval Models from Incomplete Relevance Labels", + "abstract": [ + "Recent deployment of efficient billion-scale approximate nearest neighbor (ANN) search algorithms on GPUs has motivated information retrieval researchers to develop neural ranking models that learn low-dimensional dense representations for queries and documents and use ANN search for retrieval.", + "However, optimizing these dense retrieval models poses several challenges including negative sampling for (pair-wise) training.", + "A recent model, called ANCE, successfully uses dynamic negative sampling using ANN search.", + "This paper improves upon ANCE by proposing a robust negative sampling strategy for scenarios where the training data lacks complete relevance annotations.", + "This is of particular importance as obtaining large-scale training data with complete relevance judgment is extremely expensive.", + "Our model uses a small validation set with complete relevance judgments to accurately estimate a negative sampling distribution for dense retrieval models.", + "We also explore leveraging a lexical matching signal during training and pseudo-relevance feedback during evaluation for improved performance.", + "Our experiments on the TREC Deep Learning Track benchmarks demonstrate the effectiveness of our solutions." + ] + }, + { + "title": "Intra-Document Cascading: Learning to Select Passages for Neural Document Ranking", + "abstract": [ + "An emerging recipe for achieving state-of-the-art effectiveness in neural document re-ranking involves utilizing large pre-trained language models - e.g., BERT - to evaluate all individual passages in the document and then aggregating the outputs by pooling or additional Transformer layers.", + "A major drawback of this approach is high query latency due to the cost of evaluating every passage in the document with BERT.", + "To make matters worse, this high inference cost and latency varies based on the length of the document, with longer documents requiring more time and computation.", + "To address this challenge, we adopt an intra-document cascading strategy, which prunes passages of a candidate document using a less expensive model, called ESM, before running a scoring model that is more expensive and effective, called ETM.", + "We found it best to train ESM (short for Efficient Student Model) via knowledge distillation from the ETM (short for Effective Teacher Model) e.g., BERT.", + "This pruning allows us to only run the ETM model on a smaller set of passages whose size does not vary by document length.", + "Our experiments on the MS MARCO and TREC Deep Learning Track benchmarks suggest that the proposed Intra-Document Cascaded Ranking Model (IDCM) leads to over 400% lower query latency by providing essentially the same effectiveness as the state-of-the-art BERT-based document ranking models." + ] + }, + { + "title": "Analysing Mixed Initiatives and Search Strategies during Conversational Search", + "abstract": [ + "Information seeking conversations between users and Conversational Search Agents (CSAs) consist of multiple turns of interaction.", + "While users initiate a search session, ideally a CSA should sometimes take the lead in the conversation by obtaining feedback from the user by offering query suggestions or asking for query clarifications i.e. mixed initiative.", + "This creates the potential for more engaging conversational searches, but substantially increases the complexity of modelling and evaluating such scenarios due to the large interaction space coupled with the trade-offs between the costs and benefits of the different interactions.", + "In this paper, we present a model for conversational search -- from which we instantiate different observed conversational search strategies, where the agent elicits: (i) Feedback-First, or (ii) Feedback-After.", + "Using 49 TREC WebTrack Topics, we performed an analysis comparing how well these different strategies combine with different mixed initiative approaches: (i) Query Suggestions vs. (ii) Query Clarifications.", + "Our analysis reveals that there is no superior or dominant combination, instead it shows that query clarifications are better when asked first, while query suggestions are better when asked after presenting results.", + "We also show that the best strategy and approach depends on the trade-offs between the relative costs between querying and giving feedback, the performance of the initial query, the number of assessments per query, and the total amount of gain required.", + "While this work highlights the complexities and challenges involved in analyzing CSAs, it provides the foundations for evaluating conversational strategies and conversational search agents in batch/offline settings." + ] + }, + { + "title": "Passage Retrieval for Outside-Knowledge Visual Question Answering", + "abstract": [ + "In this work, we address multi-modal information needs that contain text questions and images by focusing on passage retrieval for outside-knowledge visual question answering.", + "This task requires access to outside knowledge, which in our case we define to be a large unstructured passage collection.", + "We first conduct sparse retrieval with BM25 and study expanding the question with object names and image captions.", + "We verify that visual clues play an important role and captions tend to be more informative than object names in sparse retrieval.", + "We then construct a dual-encoder dense retriever, with the query encoder being LXMERT, a multi-modal pre-trained transformer.", + "We further show that dense retrieval significantly outperforms sparse retrieval that uses object expansion.", + "Moreover, dense retrieval matches the performance of sparse retrieval that leverages human-generated captions." + ] + }, + { + "title": "Towards Multi-Modal Conversational Information Seeking", + "abstract": [ + "Recent research on conversational information seeking (CIS) mostly focuses on uni-modal interactions and information items.", + "This per- spective paper highlights the importance of moving towards de- veloping and evaluating multi-modal conversational information seeking (MMCIS) systems as they enable us to leverage richer context, overcome errors, and increase accessibility.", + "We bridge the gap between the multi-modal and CIS research and provide a formal definition for MMCIS.", + "We discuss potential opportunities and research challenges in designing, implementing, and evaluating MMCIS systems.", + "Based on this research, we propose and implement a practical open-source framework for facilitating MMCIS research." + ] + }, + { + "title": "A comparison of skin dose estimation between thermoluminescent dosimeter and treatment planning system in prostatic cancer: A brachytherapy technique", + "abstract": [ + "Aims: This study aimed to compare the skin dose calculated by treatment planning system (TPS) and measured with thermoluminescent dosimeters (TLDs) in brachytherapy of prostatic cancer to show the skin TLD dosimetry as an appropriate quality assurance procedure for TPS dose calculations.", + "Methods: The skin dose of 15 patients with prostatic cancer treated by high dose rate brachytherapy technique was assessed by two types of TLD dosimeters (GR-200 and TLD-100).", + "The TLDs were placed on the patient\u2019s skin at three different points (anterior, left, and right) using five TLDs for each point.", + "The dose values of TLDs and TPS were compared using paired t-test and the percentages of difference were reported.", + "Results: There was a good agreement between TPS calculations and TLDs measurements for both of the GR-200 and TLD-100 dosimeters.", + "The mean skin dose values for anterior, left, and right points were 65.06\u00b121.88, 13.88\u00b14.1, and 10.05\u00b14.39 cGy, respectively, for TPS.", + "These values were 65.70\u00b123.2, 14.51\u00b14.3, and 10.54\u00b15 cGy for GR-200, and 64.22\u00b123.5, 13.43\u00b14.4, and 9.99\u00b14.1 cGy for TLD-100, respectively.", + "Conclusion: The TPS skin dose calculations in brachytherapy of prostatic cancer had a good agreement with the TLD-100 and GR-200 measurements at the three different points on patients\u2019 skin.", + "TLD-100 had lower differences with TPS calculations compared to GR-200.", + "Relevance for Patients: The outcome of this research shows that for people with prostatic cancer, TPS can estimate accurately the skin dose of different points including anterior, left, and right in brachytherapy technique." + ] + }, + { + "title": "Radiation protection and cytotoxicity effects of different concentrations of cerium oxide nanoparticles in aqueous solution combined with sodium dodecyl sulphate in Vero cells irradiated with 18 MV beams", + "abstract": [ + "Background: This study aimed to assess and compare the radioprotective and cytotoxic effects of various concentrations of cerium oxide nanoparticles (CONPs) in aqueous solution combined with sodium dodecyl sulphate (SDS) against high energy X-ray beams in Vero cells.", + "Materials and Methods: The scanner electron microscopy (SEM) method was used to analyze the properties of CONPs.", + "The cells were incubated with different concentrations of CONPs in aqueous solution combined with SDS.", + "The non-toxic CONPs concentrations in Vero normal cells were determined using MTT assay.", + "The cell\u2019s uptake was measured by an UV/VIS absorption spectrophotometry.", + "The cells were irradiated with different doses of 18 MV photon (1, 2, and 3 Gy), and their viabilities at various concentrations were measured to evaluate the radiation protection effects of CONPs.", + "Results: The CONPs concentrations lower than 600 \u03bcg/ml were referred as non-toxic effects regarding MTT results.", + "The 600 \u03bcg/ml was regarded as the highest radioprotection effect among the non-toxic concentrations (P-value\u02c20.05).", + "The average percentage of cell viability improvement was estimated as 17, 23.61, and 27.21% for 1, 2, and 3 Gy doses, respectively, compared to the control group (with no CONPs).", + "Pearson\u2019s correlation coefficients between the CONPs concentration and cell viability were obtained as 0.96, 0.99, and 0.99 for 1, 2, and 3 Gy doses, respectively; showing that the increased concentration leads to an increase in higher radioprotection.", + "Conclusion: The 600 \u03bcg/ml of CONPs aqueous solution combined with SDS, as a stable non-toxic concentration, has the highest radiation protection effect when exposed to high-energy photon beams.", + "So, this concentration can be considered as an appropriate candidate of radioprotection for further research." + ] + }, { "title": "Analyzing clarification in asynchronous information\u2010seeking conversations", "abstract": [ @@ -226,49 +719,917 @@ ] }, { - "title": "FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation", + "title": "Estimating Radiotherapy-Induced Secondary Cancer Risk Arising from Brain Irradiation at High Energy: A Monte Carlo Study", "abstract": [ - "Retrieval-augmented generation models offer many bene\ufb01ts over standalone language models: besides a textual answer to a given query they provide provenance items retrieved from an updateable knowledge base.", - "However, they are also more complex systems and need to handle long inputs.", - "In this work, we introduce FiD-Light to strongly increase the ef\ufb01ciency of the state-of-the-art retrieval-augmented FiD model, while maintaining the same level of effectiveness.", - "Our FiD-Light model constrains the information \ufb02ow from the encoder (which encodes passages separately) to the decoder (using concatenated encoded representations).", - "Fur-thermore, we adapt FiD-Light with re-ranking capabilities through textual source pointers, to improve the top-ranked provenance precision.", - "Our experiments on a diverse set of seven knowledge intensive tasks (KILT) show FiD-Light consistently improves the Pareto frontier between query latency and effectiveness.", - "FiD-Light with source pointing sets substantial new state-of-the-art results on six KILT tasks for combined text generation and provenance retrieval evaluation, while maintaining reasonable ef\ufb01ciency." + "Background: The present study aims to determine the whole-body out-of-field photon dose equivalents of high-energy conventional radiation therapy treatment.", + "Also, it is tried to estimate the probability of fatal secondary cancer risk for the susceptible organs using a Monte Carlo (MC) code.", + "\nMaterials and methods: An Monte Carlo N-Particle eXtended (MCNPX)-based model of 18-MV Medical Linear Accelerator (LINAC) was created to calculate the out-of-field photon dose equivalent at the locations of fascinating organs in the mathematical female Medical Internal Radiation Dosimetry (MIRD) phantom.", + "Then, the secondary malignancies risk was estimated based on out-of-field doses and radiation risk coefficients according to the National Council of Radiation Protection and Measurements (NCRP).", + "\nResults: The average photon equivalent dose in out-of-field organs was about 3.25 mSv/Gy, ranging from 0.23 to 37.2 mSv/Gy, respectively, for the organs far from the Planning Target Volume (PTV) (Eyes) and those close to the treatment field (rectum).", + "The entire secondary cancer risk for the 60 Gy prescribed dose to isocenter was obtained as 2.9987%.", + "Here, the maximum doses among off-field organs were related to stomach (0.0805%), lung (0.0601%), and thyroid (0.0404%).", + "\nConclusion: Regarding the estimated values for the probability of secondary cancer risk, it is suggested to perform a long-term follow-up of brain cancer patients regarding the prevalence of thyroid, stomach, and lung cancer after completing the treatment course." ] }, { - "title": "Generalizing Discriminative Retrieval Models using Generative Tasks", + "title": "Estimating the Entrance Surface Dose in the Eyes, Thyroid, and Parotid Gland Regions in Adult and Pediatric Groups: A Cone-Beam Computed Tomography Technique", "abstract": [ - "Information Retrieval has a long history of applying either discriminative or generative modeling to retrieval and ranking tasks.", - "Recent developments in transformer architectures and multi-task learning techniques have dramatically improved our ability to train effective neural models capable of resolving a wide variety of tasks using either of these paradigms.", - "In this paper, we propose a novel multi-task learning approach which can be used to produce more effective neural ranking models.", - "The key idea is to improve the quality of the underlying transformer model by cross-training a retrieval task and one or more complementary language generation tasks.", - "By targeting the training on the encoding layer in the transformer architecture, our experimental results show that the proposed multi-task learning approach consistently improves retrieval effectiveness on the targeted collection and can easily be re-targeted to new ranking tasks.", - "We provide an in-depth analysis showing how multi-task learning modifies model behaviors, resulting in more general models." + "Purpose: This study aimed to determine the Entrance Surface Dose (ESD) of sensitive organs in Cone-Beam Computed Tomography (CBCT) imaging of the maxillofacial region in the two age groups of adult and pediatric.", + "\nMaterials and Methods: In this work, the measurements were performed using Thermo Luminescent Dosimeters (TLD-GR200).", + "The imaging was performed using a PROMAX 3D CBCT scanner for 30 adults and 20 pediatric patients.", + "The ESD value for each patient in the region of eyes, thyroid, and parotid glands was measured by 15 TLDs during CBCT of maxillofacial.", + "\nResults: The highest and lowest mean values of ESDs were related to the parotid and thyroid gland regions in adults, 4.77 \u00b1 0.61 mGy and 0.37 \u00b1 0.16 mGy, respectively.", + "In addition, these values were obtained 2.97 \u00b1 0.36 mGy and 0.35 \u00b1 0.12 mGy in pediatric groups as the highest and lowest values in that order.", + "The results showed that the ESD values of the parotid gland regions in maxilla and mandible examinations had a significant difference (P <0.05).", + "In addition, there was a significant difference between the ESD values of the parotid gland regions among the adults and pediatric groups (P <0.05).", + "\nConclusion: According to the results, the ESD values in both age groups were higher in the parotid gland region during maxillofacial CBCT examinations.", + "Therefore, it is recommended to set radiation parameters like mAs as low as possible for reducing the patient dose, especially pediatric patients due to the more sensitive organs." + ] + }, + { + "title": "Analyzing and Learning from User Interactions for Search Clarification", + "abstract": [ + "Asking clarifying questions in response to search queries has been recognized as a useful technique for revealing the underlying intent of the query.", + "Clarification has applications in retrieval systems with different interfaces, from the traditional web search interfaces to the limited bandwidth interfaces as in speech-only and small screen devices.", + "Generation and evaluation of clarifying questions have been recently studied in the literature.", + "However, user interaction with clarifying questions is relatively unexplored.", + "In this paper, we conduct a comprehensive study by analyzing large-scale user interactions with clarifying questions in a major web search engine.", + "In more detail, we analyze the user engagements received by clarifying questions based on different properties of search queries, clarifying questions, and their candidate answers.", + "We further study click bias in the data, and show that even though reading clarifying questions and candidate answers does not take significant efforts, there still exist some position and presentation biases in the data.", + "We also propose a model for learning representation for clarifying questions based on the user interaction data as implicit feedback.", + "The model is used for re-ranking a number of automatically generated clarifying questions for a given query.", + "Evaluation on both click data and human labeled data demonstrates the high quality of the proposed method." + ] + }, + { + "title": "Conformer-Kernel with Query Term Independence for Document Retrieval", + "abstract": [ + "The Transformer-Kernel (TK) model has demonstrated strong reranking performance on the TREC Deep Learning benchmark---and can be considered to be an efficient (but slightly less effective) alternative to BERT-based ranking models.", + "In this work, we extend the TK architecture to the full retrieval setting by incorporating the query term independence assumption.", + "Furthermore, to reduce the memory complexity of the Transformer layers with respect to the input sequence length, we propose a new Conformer layer.", + "We show that the Conformer's GPU memory requirement scales linearly with input sequence length, making it a more viable option when ranking long documents.", + "Finally, we demonstrate that incorporating explicit term matching signal into the model can be particularly useful in the full retrieval setting.", + "We present preliminary results from our work in this paper." + ] + }, + { + "title": "Learning a Joint Search and Recommendation Model from User-Item Interactions", + "abstract": [ + "Existing learning to rank models for information retrieval are trained based on explicit or implicit query-document relevance information.", + "In this paper, we study the task of learning a retrieval model based on user-item interactions.", + "Our model has potential applications to the systems with rich user-item interaction data, such as browsing and recommendation, in which having an accurate search engine is desired.", + "This includes media streaming services and e-commerce websites among others.", + "Inspired by the neural approaches to collaborative filtering and the language modeling approaches to information retrieval, our model is jointly optimized to predict user-item interactions and reconstruct the item textual descriptions.", + "In more details, our model learns user and item representations such that they can accurately predict future user-item interactions, while generating an effective unigram language model for each item.", + "Our experiments on four diverse datasets in the context of movie and product search and recommendation demonstrate that our model substantially outperforms competitive retrieval baselines, in addition to providing comparable performance to state-of-the-art hybrid recommendation models." + ] + }, + { + "title": "Common Conversational Community Prototype: Scholarly Conversational Assistant", + "abstract": [ + "This paper discusses the potential for creating academic resources (tools, data, and evaluation approaches) to support research in conversational search, by focusing on realistic information needs and conversational interactions.", + "Specifically, we propose to develop and operate a prototype conversational search system for scholarly activities.", + "This Scholarly Conversational Assistant would serve as a useful tool, a means to create datasets, and a platform for running evaluation challenges by groups across the community.", + "This article results from discussions of a working group at Dagstuhl Seminar 19461 on Conversational Search." + ] + }, + { + "title": "Generating ClarifyingQuestions for Information Retrieval", + "abstract": [ + "Search queries are often short, and the underlying user intent may be ambiguous.", + "This makes it challenging for search engines to predict possible intents, only one of which may pertain to the current user.", + "To address this issue, search engines often diversify the result list and present documents relevant to multiple intents of the query.", + "An alternative approach is to ask the user a question to clarify her information need.", + "Asking clarifying questions is particularly important for scenarios with \u201climited bandwidth\u201d interfaces, such as speech-only and small-screen devices.", + "In addition, our user studies and large-scale online experiments show that asking clarifying questions is also useful in web search.", + "Although some recent studies have pointed out the importance of asking clarifying questions, generating them for open-domain search tasks remains unstudied and is the focus of this paper.", + "Lack of training data even within major search engines for this task makes it challenging.", + "To mitigate this issue, we first identify a taxonomy of clarification for open-domain search queries by analyzing large-scale query reformulation data sampled from Bing search logs.", + "This taxonomy leads us to a set of question templates and a simple yet effective slot filling algorithm.", + "We further use this model as a source of weak supervision to automatically generate clarifying questions for training.", + "Furthermore, we propose supervised and reinforcement learning models for generating clarifying questions learned from weak supervision data.", + "We also investigate methods for generating candidate answers for each clarifying question, so users can select from a set of predefined answers.", + "Human evaluation of the clarifying questions and candidate answers for hundreds of search queries demonstrates the effectiveness of the proposed solutions.", + "ACM Reference Format: Hamed Zamani, Susan T. Dumais, Nick Craswell, Paul N. Bennett, and Gord Lueck.", + "2020.", + "Generating Clarifying Questions for Information Retrieval.", + "In Proceedings of The Web Conference 2020 (WWW \u201920), April 20\u201324, 2020, Taipei, Taiwan.", + "ACM, New York, NY, USA, 11 pages.", + "https://doi.org/10.1145/" + ] + }, + { + "title": "A Reinforcement Learning Framework for Relevance Feedback", + "abstract": [ + "We present RML, the first known general reinforcement learning framework for relevance feedback that directly optimizes any desired retrieval metric, including precision-oriented, recall-oriented, and even diversity metrics: RML can be easily extended to directly optimize any arbitrary user satisfaction signal.", + "Using the RML framework, we can select effective feedback terms and weight them appropriately, improving on past methods that fit parameters to feedback algorithms using heuristic approaches or methods that do not directly optimize for retrieval performance.", + "Learning an effective relevance feedback model is not trivial since the true feedback distribution is unknown.", + "Experiments on standard TREC collections compare RML to existing feedback algorithms, demonstrate the effectiveness of RML at optimizing for MAP and \u03b1-n DCG, and show the impact on related measures." + ] + }, + { + "title": "Special Issue Proposal: Conversational Search and Recommendation", + "abstract": [ + "The rapid growth in speech and small screen interfaces, particularly on mobile devices, has significantly influenced the way users interact with intelligent systems to satisfy their information needs.", + "The growing interest in personal digital assistants, such as Amazon Alexa, Apple Siri, Google Assistant, and Microsoft Cortana, demonstrates the willingness of users to employ conversational interactions.", + "In this special issue, we focus on interactions with information seeking goals.", + "This includes conversational search and recommendation.", + "Given the importance of the topic to both academia and industry and the recent availability of multiple public datasets in this area, we believe that the time is right to propose a special issue on this topic, and ACM Transactions on Information Systems is the perfect venue for it." + ] + }, + { + "title": "Conformer-Kernel with Query Term Independence at TREC 2020 Deep Learning Track", + "abstract": [ + "We benchmark Conformer-Kernel models under the strict blind evaluation setting of the TREC 2020 Deep Learning track.", + "In particular, we study the impact of incorporating: (i) Explicit term matching to complement matching based on learned representations (i.e., the \"Duet principle\"), (ii) query term independence (i.e., the \"QTI assumption\") to scale the model to the full retrieval setting, and (iii) the ORCAS click data as an additional document description field.", + "We find evidence which supports that all three aforementioned strategies can lead to improved retrieval quality." + ] + }, + { + "title": "Generating Clarifying Questions for Information Retrieval", + "abstract": [ + "Search queries are often short, and the underlying user intent may be ambiguous.", + "This makes it challenging for search engines to predict possible intents, only one of which may pertain to the current user.", + "To address this issue, search engines often diversify the result list and present documents relevant to multiple intents of the query.", + "An alternative approach is to ask the user a question to clarify her information need.", + "Asking clarifying questions is particularly important for scenarios with \u201climited bandwidth\u201d interfaces, such as speech-only and small-screen devices.", + "In addition, our user studies and large-scale online experiments show that asking clarifying questions is also useful in web search.", + "Although some recent studies have pointed out the importance of asking clarifying questions, generating them for open-domain search tasks remains unstudied and is the focus of this paper.", + "Lack of training data even within major search engines for this task makes it challenging.", + "To mitigate this issue, we first identify a taxonomy of clarification for open-domain search queries by analyzing large-scale query reformulation data sampled from Bing search logs.", + "This taxonomy leads us to a set of question templates and a simple yet effective slot filling algorithm.", + "We further use this model as a source of weak supervision to automatically generate clarifying questions for training.", + "Furthermore, we propose supervised and reinforcement learning models for generating clarifying questions learned from weak supervision data.", + "We also investigate methods for generating candidate answers for each clarifying question, so users can select from a set of pre-defined answers.", + "Human evaluation of the clarifying questions and candidate answers for hundreds of search queries demonstrates the effectiveness of the proposed solutions." + ] + }, + { + "title": "Guided Transformer: Leveraging Multiple External Sources for Representation Learning in Conversational Search", + "abstract": [ + "Asking clarifying questions in response to ambiguous or faceted queries has been recognized as a useful technique for various information retrieval systems, especially conversational search systems with limited bandwidth interfaces.", + "Analyzing and generating clarifying questions have been studied recently but the accurate utilization of user responses to clarifying questions has been relatively less explored.", + "In this paper, we enrich the representations learned by Transformer networks using a novel attention mechanism from external information sources that weights each term in the conversation.", + "We evaluate this Guided Transformer model in a conversational search scenario that includes clarifying questions.", + "In our experiments, we use two separate external sources, including the top retrieved documents and a set of different possible clarifying questions for the query.", + "We implement the proposed representation learning model for two downstream tasks in conversational search; document retrieval and next clarifying question selection.", + "Our experiments use a public dataset for search clarification and demonstrate significant improvements compared to competitive baselines." + ] + }, + { + "title": "MIMICS: A Large-Scale Data Collection for Search Clarification", + "abstract": [ + "Search clarification has recently attracted much attention due to its applications in search engines.", + "It has also been recognized as a major component in conversational information seeking systems.", + "Despite its importance, the research community still feels the lack of a large-scale dataset for studying different aspects of search clarification.", + "In this paper, we introduce MIMICS, a collection of search clarification datasets for real web search queries sampled from the Bing query logs.", + "Each clarification in MIMICS is generated by a Bing production algorithm and consists of a clarifying question and up to five candidate answers.", + "MIMICS contains three datasets: (1) MIMICS-Click includes over 400k unique queries, their associated clarification panes, and the corresponding aggregated user interaction signals (i.e., clicks). (", + "2) MIMICS-ClickExplore is an exploration data that includes aggregated user interaction signals for over 60k unique queries, each with multiple clarification panes. (", + "3) MIMICS-Manual includes over 2k unique real search queries.", + "Each query-clarification pair in this dataset has been manually labeled by at least three trained annotators.", + "It contains graded quality labels for the clarifying question, the candidate answer set, and the landing result page for each candidate answer.", + "MIMICS is publicly available for research purposes, thus enables researchers to study a number of tasks related to search clarification, including clarification generation and selection, user engagement prediction for clarification, click models for clarification, and analyzing user interactions with search clarification.", + "We also release the results returned by the Bing's web search API for all the queries in MIMICS.", + "This would allow researchers to utilize search results for the tasks related to search clarification." + ] + }, + { + "title": "Recipe Retrieval with Visual Query of Ingredients", + "abstract": [ + "Recipe retrieval is a representative and useful application of cross-modal information retrieval.", + "Recent studies have proposed frameworks for retrieving images of cuisines given textual ingredient lists and instructions.", + "However, the textual form of ingredients easily causes information loss or inaccurate description, especially for novices of cookery who are often the main users of recipe retrieval systems.", + "In this paper, we revisit the task of recipe retrieval by taking images of ingredients as input queries, and retrieving cuisine images by incorporating visual information of ingredients through a deep convolutional neural network.", + "We build an image-to-image recipe retrieval system to validate the effect of ingredient image queries.", + "We further combine the proposed solution with a state-of-the-art cross-modal recipe retrieval model to improve the overall performance of the recipe retrieval task." + ] + }, + { + "title": "Local Self-Attention over Long Text for Efficient Document Retrieval", + "abstract": [ + "Neural networks, particularly Transformer-based architectures, have achieved significant performance improvements on several retrieval benchmarks.", + "When the items being retrieved are documents, the time and memory cost of employing Transformers over a full sequence of document terms can be prohibitive.", + "A popular strategy involves considering only the first n terms of the document.", + "This can, however, result in a biased system that under retrieves longer documents.", + "In this work, we propose a local self-attention which considers a moving window over the document terms and for each term attends only to other terms in the same window.", + "This local attention incurs a fraction of the compute and memory cost of attention over the whole document.", + "The windowed approach also leads to more compact packing of padded documents in minibatches resulting in additional savings.", + "We also employ a learned saturation function and a two-staged pooling strategy to identify relevant regions of the document.", + "The Transformer-Kernel pooling model with these changes can efficiently elicit relevance information from documents with thousands of tokens.", + "We benchmark our proposed modifications on the document ranking task from the TREC 2019 Deep Learning track and observe significant improvements in retrieval quality as well as increased retrieval of longer documents at moderate increase in compute and memory costs." + ] + }, + { + "title": "Doses Delivered to Patients and Associated Risks from Conventional Radiological Scans in Yasuj City, Iran", + "abstract": [ + "The above article has been withdrawn on authors\u2019 request.", + "Hassanvand A, Masjedi HR, Zamani H, et al. Doses delivered to patients and associated risks from conventional radiological scans in Yasuj city, Iran.", + "J Evolution Med Dent Sci 2020;9(40):2997-3003, DOI: 10.14260/jemds/2020/656" + ] + }, + { + "title": "Investigating the Successes and Failures of BERT for Passage Re-Ranking", + "abstract": [ + "The bidirectional encoder representations from transformers (BERT) model has recently advanced the state-of-the-art in passage re-ranking.", + "In this paper, we analyze the results produced by a fine-tuned BERT model to better understand the reasons behind such substantial improvements.", + "To this aim, we focus on the MS MARCO passage re-ranking dataset and provide potential reasons for the successes and failures of BERT for retrieval.", + "In more detail, we empirically study a set of hypotheses and provide additional analysis to explain the successful performance of BERT." + ] + }, + { + "title": "Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering", + "abstract": [ + "Multi-hop question answering (QA) requires an information retrieval (IR) system that can find multiple supporting evidence needed to answer the question, making the retrieval process very challenging.", + "This paper introduces an IR technique that uses information of entities present in the initially retrieved evidence to learn to \u2018hop\u2019 to other relevant evidence.", + "In a setting, with more than 5 million Wikipedia paragraphs, our approach leads to significant boost in retrieval performance.", + "The retrieved evidence also increased the performance of an existing QA model (without any training) on the benchmark by 10.59 F1." + ] + }, + { + "title": "Asking Clarifying Questions in Open-Domain Information-Seeking Conversations", + "abstract": [ + "Users often fail to formulate their complex information needs in a single query.", + "As a consequence, they may need to scan multiple result pages or reformulate their queries, which may be a frustrating experience.", + "Alternatively, systems can improve user satisfaction by proactively asking questions of the users to clarify their information needs.", + "Asking clarifying questions is especially important in conversational systems since they can only return a limited number of (often only one) result(s).", + "In this paper, we formulate the task of asking clarifying questions in open-domain information-seeking conversational systems.", + "To this end, we propose an offline evaluation methodology for the task and collect a dataset, called Qulac, through crowdsourcing.", + "Our dataset is built on top of the TREC Web Track 2009-2012 data and consists of over 10K question-answer pairs for 198 TREC topics with 762 facets.", + "Our experiments on an oracle model demonstrate that asking only one good question leads to over 170% retrieval performance improvement in terms of P@1, which clearly demonstrates the potential impact of the task.", + "We further propose a retrieval framework consisting of three components: question retrieval, question selection, and document retrieval.", + "In particular, our question selection model takes into account the original query and previous question-answer interactions while selecting the next question.", + "Our model significantly outperforms competitive baselines.", + "To foster research in this area, we have made Qulac publicly available." + ] + }, + { + "title": "Macaw: An Extensible Conversational Information Seeking Platform", + "abstract": [ + "Conversational information seeking (CIS) has been recognized as a major emerging research area in information retrieval.", + "Such research will require data and tools, to allow the implementation and study of conversational systems.", + "This paper introduces Macaw, an open-source framework with a modular architecture for CIS research.", + "Macaw supports multi-turn, multi-modal, and mixed-initiative interactions, and enables research for tasks such as document retrieval, question answering, recommendation, and structured data exploration.", + "It has a modular design to encourage the study of new CIS algorithms, which can be evaluated in batch mode.", + "It can also integrate with a user interface, which allows user studies and data collection in an interactive mode, where the back end can be fully algorithmic or a wizard of oz setup.", + "Macaw is distributed under the MIT License." + ] + }, + { + "title": "Performance Prediction for Non-Factoid Question Answering", + "abstract": [ + "Estimating the quality of a result list, often referred to as query performance prediction (QPP), is a challenging and important task in information retrieval.", + "It can be used as feedback to users, search engines, and system administrators.", + "Although predicting the performance of retrieval models has been extensively studied for the ad-hoc retrieval task, the effectiveness of performance prediction methods for question answering (QA) systems is relatively unstudied.", + "The short length of answers, the dominance of neural models in QA, and the re-ranking nature of most QA systems make performance prediction for QA a unique, important, and technically interesting task.", + "In this paper, we introduce and motivate the task of performance prediction for non-factoid question answering and propose a neural performance predictor for this task.", + "Our experiments on two recent datasets demonstrate that the proposed model outperforms competitive baselines in all settings." + ] + }, + { + "title": "Neural models for information retrieval without labeled data", + "abstract": [ + "Recent developments of machine learning models, and in particular deep neural networks, have yielded significant improvements on several computer vision, natural language processing, and speech recognition tasks.", + "Progress with information retrieval (IR) tasks has been slower, however, due to the lack of large-scale training data as well as neural network models specifically designed for effective information retrieval [9].", + "In this dissertation, we address these two issues by introducing task-specific neural network architectures for a set of IR tasks and proposing novel unsupervised or weakly supervised solutions for training the models.", + "The proposed learning solutions do not require labeled training data.", + "Instead, in our weak supervision approach, neural models are trained on a large set of noisy and biased training data obtained from external resources, existing models, or heuristics.", + "We first introduce relevance-based embedding models [3] that learn distributed representations for words and queries.", + "We show that the learned representations can be effectively employed for a set of IR tasks, including query expansion, pseudo-relevance feedback, and query classification [1, 2].", + "We further propose a standalone learning to rank model based on deep neural networks [5, 8].", + "Our model learns a sparse representation for queries and documents.", + "This enables us to perform efficient retrieval by constructing an inverted index in the learned semantic space.", + "Our model outperforms state-of-the-art retrieval models, while performing as efficiently as term matching retrieval models.", + "We additionally propose a neural network framework for predicting the performance of a retrieval model for a given query [7].", + "Inspired by existing query performance prediction models, our framework integrates several information sources, such as retrieval score distribution and term distribution in the top retrieved documents.", + "This leads to state-of-the-art results for the performance prediction task on various standard collections.", + "We finally bridge the gap between retrieval and recommendation models, as the two key components in most information systems.", + "Search and recommendation often share the same goal: helping people get the information they need at the right time.", + "Therefore, joint modeling and optimization of search engines and recommender systems could potentially benefit both systems [4].", + "In more detail, we introduce a retrieval model that is trained using user-item interaction (e.g., recommendation data), with no need to query-document relevance information for training [6].", + "Our solutions and findings in this dissertation smooth the path towards learning efficient and effective models for various information retrieval and related tasks, especially when large-scale training data is not available." + ] + }, + { + "title": "Recommender Systems Fairness Evaluation via Generalized Cross Entropy", + "abstract": [ + "Fairness in recommender systems has been considered with respect to sensitive attributes of users (e.g., gender, race) or items (e.g., revenue in a multistakeholder setting).", + "Regardless, the concept has been commonly interpreted as some form of equality -- i.e., the degree to which the system is meeting the information needs of all its users in an equal sense.", + "In this paper, we argue that fairness in recommender systems does not necessarily imply equality, but instead it should consider a distribution of resources based on merits and needs.", + "\nWe present a probabilistic framework based on generalized cross entropy to evaluate fairness of recommender systems under this perspective, where we show that the proposed framework is flexible and explanatory by allowing to incorporate domain knowledge (through an ideal fair distribution) that can help to understand which item or user aspects a recommendation algorithm is over- or under-representing.", + "Results on two real-world datasets show the merits of the proposed evaluation framework both in terms of user and item fairness." + ] + }, + { + "title": "Analyzing and Predicting News Popularity in an Instant Messaging Service", + "abstract": [ + "With widespread use of mobile devices, instant messaging (IM) services have recently attracted a great deal of attention by millions of users.", + "This has motivated news agencies to share their contents via such platforms in addition to their websites and popular social media.", + "As a result, thousands of users nowadays follow the news agencies through their verified channels in IM services.", + "However, user interactions with such platforms is relatively unstudied.", + "In this paper, we provide an initial study to analyze and predict news popularity in an instant messaging service.", + "To this aim, we focus on Telegram, a popular IM service with 200 million monthly active users.", + "We explore the differences between news popularity analysis in Telegram and typical social media, such as Twitter, and highlight its unique characteristics.", + "We perform our analysis on the data we collected from four diverse news agencies.", + "Following our analysis, we study the task of news popularity prediction in Telegram and show that the performance of the prediction models can be substantially improved by learning from the data of multiple news agencies using multi-task learning.", + "To foster research in this area, we have made the collected data publicly available." + ] + }, + { + "title": "UvA-DARE (Digital Neural Ranking Models with Weak Supervision", + "abstract": [ + "Learning state-of-the-art deep neural network models requires a large amounts of labeled data, which is not always readily available and can be expensive to obtain.", + "To cir-cumvent the lack of human-labeled training examples, unsupervised learning methods aim to model the underlying data distribution, thus learning powerful feature representations of the input data, which can be helpful for building more accurate discriminative models especially when little or even no supervised data is available.", + "A large group of unsupervised neural models seeks to exploit the implicit internal structure of the input data, which in turn requires customized formulation of the training objective (loss function), targeted network architectures and often non-trivial training setups.", + "Despite the advances in computer vision, speech recognition, and NLP tasks using unsupervised deep neural networks, such advances have not been observed in core information retrieval (IR) problems, such as ranking.", + "A plausible explanation is the complexity of the ranking problem in IR, in the sense that it is not obvious how to learn a ranking model from queries and documents when no supervision in form of the relevance information is available.", + "To overcome this issue, in this paper, we propose to leverage large amounts of unsupervised data to infer \u201cnoisy\u201d or \u201cweak\u201d labels and use that signal for learning supervised models as if we had the ground truth labels.", + "In particular, we use classic unsupervised IR models as a weak supervision signal for training deep neural ranking models.", + "Weak supervision here refers to a learning approach that creates its own training data by heuristically retrieving documents for a large query set.", + "This training data is created au-tomatically, thus it is possible to generate billions of training instances with almost no cost.", + "As training" + ] + }, + { + "title": "Citation Worthiness of Sentences in Scientific Reports", + "abstract": [ + "Does this sentence need citation?", + "In this paper, we introduce the task of citation worthiness for scientific texts at a sentence-level granularity.", + "The task is to detect whether a sentence in a scientific article needs to be cited or not.", + "It can be incorporated into citation recommendation systems to help automate the citation process by marking sentences where needed.", + "It may also be useful for publishers to regularize the citation process.", + "We construct a dataset using the ACL Anthology Reference Corpus; consisting of over 1.1M \"not_cite\" and 85K \"cite\" sentences.", + "We study the performance of a set of state-of-the-art sentence classifiers for the citation worthiness task and show the practical challenges.", + "We also explore section-wise difficulty of the task and analyze the performance of our best model on a published article." + ] + }, + { + "title": "Neural Query Performance Prediction with Weak Supervision", + "abstract": [ + "Predicting the performance of a retrieval engine for a given query is a fundamental and challenging task that has attracted much attention.", + "Accurate performance predictors could potentially be used in various ways, such as triggering an action, choosing the most effective ranking function per query, or selecting the best variant from multiple query formulations.", + "In this paper, we propose a general end-to-end query performance prediction framework based on neural networks, called NeuralQPP.", + "Our framework consists of multiple components, each learning a representation suitable for performance prediction.", + "These representations are then aggregated and fed into a prediction sub-network.", + "We train our models with multiple weak supervision signals, which is an unsupervised learning approach that uses the existing unsupervised performance predictors as weak labelers.", + "We also propose a simple yet effective component dropout technique to regularize our model.", + "Our experiments on four newswire and web collections demonstrate that NeuralQPP significantly outperforms state-of-the-art baselines, in nearly all cases.", + "Furthermore, we thoroughly analyze the effectiveness of each component, each weak supervision signal, and their combinations in our experiments." + ] + }, + { + "title": "Neural Ranking Models with Weak Supervision", + "abstract": [ + "?", + "Learning state-of-the-art deep neural network models requires a large amounts of labeled data, which is not always readily available and can be expensive to obtain.", + "To circumvent the lack of human-labeled training examples, unsupervised learning methods aim to model the underlying data distribution, thus learning powerful feature representations of the input data, which can be helpful for building more accurate discriminative models especially when little or even no supervised data is available.", + "A large group of unsupervised neural models seeks to exploit the implicit internal structure of the input data, which in turn requires customized formulation of the training objective (loss function), targeted network architectures and often non-trivial training setups.", + "Despite the advances in computer vision, speech recognition, and NLP tasks using unsupervised deep neural networks, such advances have not been observed in core information retrieval (IR) problems, such as ranking.", + "A plausible explanation is the complexity of the ranking problem in IR, in the sense that it is not obvious how to learn a ranking model from queries and documents when no supervision in form of the relevance information is available.", + "To" + ] + }, + { + "title": "Neural Ranking Models with Weak Supervision", + "abstract": [ + "?", + "Learning state-of-the-art deep neural network models requires a large amounts of labeled data, which is not always readily available and can be expensive to obtain.", + "To circumvent the lack of human-labeled training examples, unsupervised learning methods aim to model the underlying data distribution, thus learning powerful feature representations of the input data, which can be helpful for building more accurate discriminative models especially when little or even no supervised data is available.", + "A large group of unsupervised neural models seeks to exploit the implicit internal structure of the input data, which in turn requires customized formulation of the training objective (loss function), targeted network architectures and often non-trivial training setups.", + "Despite the advances in computer vision, speech recognition, and NLP tasks using unsupervised deep neural networks, such advances have not been observed in core information retrieval (IR) problems, such as ranking.", + "A plausible explanation is the complexity of the ranking problem in IR, in the sense that it is not obvious how to learn a ranking model from queries and documents when no supervision in form of the relevance information is available.", + "To" + ] + }, + { + "title": "Recsys challenge 2018: automatic music playlist continuation", + "abstract": [ + "The ACM Recommender Systems Challenge 2018 focused on automatic music playlist continuation, which is a form of the more general task of sequential recommendation.", + "Given a playlist of arbitrary length, the challenge was to recommend up to 500 tracks that fit the target characteristics of the original playlist.", + "For the Challenge, Spotify released a dataset of one million user-created playlists, along with associated metadata.", + "Participants could submit their approaches in two tracks, i.e., main and creative tracks, where the former allowed teams to use solely the provided dataset and the latter allowed them to exploit publicly available external data too.", + "In total, 113 teams submitted 1,228 runs in the main track; 33 teams submitted 239 runs in the creative track.", + "The highest performing team in the main track achieved an R-precision of 0.2241, an NDCG of 0.3946, and an average number of recommended songs clicks of 1.784.", + "In the creative track, an R-precision of 0.2233, an NDCG of 0.3939, and a click rate of 1.785 was realized by the best team." + ] + }, + { + "title": "Target Apps Selection: Towards a Unified Search Framework for Mobile Devices", + "abstract": [ + "With the recent growth of conversational systems and intelligent assistants such as Apple Siri and Google Assistant, mobile devices are becoming even more pervasive in our lives.", + "As a consequence, users are getting engaged with the mobile apps and frequently search for an information need in their apps.", + "However, users cannot search within their apps through their intelligent assistants.", + "This requires a unified mobile search framework that identifies the target app(s) for the user's query, submits the query to the app(s), and presents the results to the user.", + "In this paper, we take the first step forward towards developing unified mobile search.", + "In more detail, we introduce and study the task of target apps selection, which has various potential real-world applications.", + "To this aim, we analyze attributes of search queries as well as user behaviors, while searching with different mobile apps.", + "The analyses are done based on thousands of queries that we collected through crowdsourcing.", + "We finally study the performance of state-of-the-art retrieval models for this task and propose two simple yet effective neural models that significantly outperform the baselines.", + "Our neural approaches are based on learning high-dimensional representations for mobile apps.", + "Our analyses and experiments suggest specific future directions in this research area." + ] + }, + { + "title": "Neural Query Performance Prediction using Weak Supervision from Multiple Signals", + "abstract": [ + "Predicting the performance of a search engine for a given query is a fundamental and challenging task in information retrieval.", + "Accurate performance predictors can be used in various ways, such as triggering an action, choosing the most effective ranking function per query, or selecting the best variant from multiple query formulations.", + "In this paper, we propose a general end-to-end query performance prediction framework based on neural networks, called NeuralQPP.", + "Our framework consists of multiple components, each learning a representation suitable for performance prediction.", + "These representations are then aggregated and fed into a prediction sub-network.", + "We train our models with multiple weak supervision signals, which is an unsupervised learning approach that uses the existing unsupervised performance predictors using weak labels.", + "We also propose a simple yet effective component dropout technique to regularize our model.", + "Our experiments on four newswire and web collections demonstrate that NeuralQPP significantly outperforms state-of-the-art baselines, in nearly every case.", + "Furthermore, we thoroughly analyze the effectiveness of each component, each weak supervision signal, and all resulting combinations in our experiments." + ] + }, + { + "title": "Theoretical Analysis of Interdependent Constraints in Pseudo-Relevance Feedback", + "abstract": [ + "Axiomatic analysis is a well-defined theoretical framework for analytical evaluation of information retrieval models.", + "The current studies in axiomatic analysis implicitly assume that the constraints (axioms) are independent.", + "In this paper, we revisit this assumption and hypothesize that there might be interdependence relationships between the existing constraints.", + "As a preliminary study, we focus on the pseudo-relevance feedback (PRF) models that have been theoretically studied using the axiomatic analysis approach.", + "In this paper, we introduce two novel interdependent PRF constraints which emphasize on the effect of existing constraints on each other.", + "We further modify two state-of-the-art PRF models, log-logistic and relevance models, in order to satisfy the proposed constraints.", + "Experiments on three TREC newswire and web collections demonstrate that the proposed modifications significantly outperform the baselines, in all cases." + ] + }, + { + "title": "Neural Ranking Models with Weak Supervision", + "abstract": [ + "?", + "Learning state-of-the-art deep neural network models requires a large amounts of labeled data, which is not always readily available and can be expensive to obtain.", + "To cir-cumvent the lack of human-labeled training examples, unsupervised learning methods aim to model the underlying data distribution, thus learning powerful feature representations of the input data, which can be helpful for building more accurate discriminative models especially when little or even no supervised data is available.", + "A large group of unsupervised neural models seeks to exploit the implicit internal structure of the input data, which in turn requires customized formulation of the training objective (loss function), targeted network architectures and often non-trivial training setups.", + "Despite the advances in computer vision, speech recognition, and NLP tasks using unsupervised deep neural networks, such advances have not been observed in core information retrieval (IR) problems, such as ranking.", + "A plausible explanation is the complexity of the ranking problem in IR, in the sense that it is not obvious how to learn a ranking model from queries and documents when no supervision in form of the relevance information is available.", + "To" + ] + }, + { + "title": "From Neural Re-Ranking to Neural Ranking: Learning a Sparse Representation for Inverted Indexing", + "abstract": [ + "The availability of massive data and computing power allowing for effective data driven neural approaches is having a major impact on machine learning and information retrieval research, but these models have a basic problem with efficiency.", + "Current neural ranking models are implemented as multistage rankers: for efficiency reasons, the neural model only re-ranks the top ranked documents retrieved by a first-stage efficient ranker in response to a given query.", + "Neural ranking models learn dense representations causing essentially every query term to match every document term, making it highly inefficient or intractable to rank the whole collection.", + "The reliance on a first stage ranker creates a dual problem: First, the interaction and combination effects are not well understood.", + "Second, the first stage ranker serves as a \"gate-keeper\" or filter, effectively blocking the potential of neural models to uncover new relevant documents.", + "In this work, we propose a standalone neural ranking model (SNRM) by introducing a sparsity property to learn a latent sparse representation for each query and document.", + "This representation captures the semantic relationship between the query and documents, but is also sparse enough to enable constructing an inverted index for the whole collection.", + "We parameterize the sparsity of the model to yield a retrieval model as efficient as conventional term based models.", + "Our model gains in efficiency without loss of effectiveness: it not only outperforms the existing term matching baselines, but also performs similarly to the recent re-ranking based neural models with dense representations.", + "Our model can also take advantage of pseudo-relevance feedback for further improvements.", + "More generally, our results demonstrate the importance of sparsity in neural IR models and show that dense representations can be pruned effectively, giving new insights about essential semantic features and their distributions." + ] + }, + { + "title": "In Situ and Context-Aware Target Apps Selection for Unified Mobile Search", + "abstract": [ + "With the recent growth in the use of conversational systems and intelligent assistants such as Google Assistant and Microsoft Cortana, mobile devices are becoming even more pervasive in our lives.", + "As a consequence, users are getting engaged with mobile apps and frequently search for an information need using different apps.", + "Recent work has stated the need for a unified mobile search system that would act as meta search on users' mobile devices: it would identify the target apps for the user's query, submit the query to the apps, and present the results to the user.", + "Moreover, mobile devices provide rich contextual information about users and their whereabouts.", + "In this paper, we introduce the task of context-aware target apps selection as part of a unified mobile search framework.", + "To this aim, we designed an in situ study to collect thousands of mobile queries enriched with mobile sensor data from 255 users during a three month period.", + "With the aid of this dataset, we were able to study user behavior as they performed cross-app search.", + "We finally study the performance of state-of-the-art retrieval models for this task and propose a simple yet effective neural model that significantly outperforms the baselines.", + "Our neural approach is based on learning high-dimensional representations for mobile apps and contextual information.", + "Furthermore, we show that incorporating context improves the performance by 20% in terms of nDCG@5, enabling the model to perform better for 57% of users.", + "Our data is publicly available for research purposes." + ] + }, + { + "title": "ACM SIGIR Student Liaison Program", + "abstract": [ + "ACM SIGIR has recently created the Student Liaison Program, a means to connect and stay connected with the student body of the information retrieval (IR) community.", + "This report provides more information about the program, introduces the founding ACM SIGIR student liaisons, and explains past, ongoing, and future activities.", + "We seek suggestions and recommendations on the current plans as well as the new ideas that fit into our mission." + ] + }, + { + "title": "Joint Modeling and Optimization of Search and Recommendation", + "abstract": [ + "Despite the somewhat different techniques used in developing search engines and recommender systems, they both follow the same goal: helping people to get the information they need at the right time.", + "Due to this common goal, search and recommendation models can potentially benefit from each other.", + "The recent advances in neural network technologies make them effective and easily extendable for various tasks, including retrieval and recommendation.", + "This raises the possibility of jointly modeling and optimizing search ranking and recommendation algorithms, with potential benefits to both.", + "In this paper, we present theoretical and practical reasons to motivate joint modeling of search and recommendation as a research direction.", + "We propose a general framework that simultaneously learns a retrieval model and a recommendation model by optimizing a joint loss function.", + "Our preliminary results on a dataset of product data indicate that the proposed joint modeling substantially outperforms the retrieval and recommendation models trained independently.", + "We list a number of future directions for this line of research that can potentially lead to development of state-of-the-art search and recommendation models." + ] + }, + { + "title": "Towards Theoretical Understanding of Weak Supervision for Information Retrieval", + "abstract": [ + "Neural network approaches have recently shown to be effective in several information retrieval (IR) tasks.", + "However, neural approaches often require large volumes of training data to perform effectively, which is not always available.", + "To mitigate the shortage of labeled data, training neural IR models with weak supervision has been recently proposed and received considerable attention in the literature.", + "In weak supervision, an existing model automatically generates labels for a large set of unlabeled data, and a machine learning model is further trained on the generated \"weak\" data.", + "Surprisingly, it has been shown in prior art that the trained neural model can outperform the weak labeler by a significant margin.", + "Although these obtained improvements have been intuitively justified in previous work, the literature still lacks theoretical justification for the observed empirical findings.", + "In this position paper, we propose to theoretically study weak supervision, in particular for IR tasks, e.g., learning to rank.", + "We briefly review a set of our recent theoretical findings that shed light on learning from weakly supervised data, and provide guidelines on how train learning to rank models with weak supervision." + ] + }, + { + "title": "An Analysis of Approaches Taken in the ACM RecSys Challenge 2018 for Automatic Music Playlist Continuation", + "abstract": [ + "The ACM Recommender Systems Challenge 2018 focused on the task of automatic music playlist continuation, which is a form of the more general task of sequential recommendation.", + "Given a playlist of arbitrary length with some additional meta-data, the task was to recommend up to 500 tracks that fit the target characteristics of the original playlist.", + "For the RecSys Challenge, Spotify released a dataset of one million user-generated playlists.", + "Participants could compete in two tracks, i.e., main and creative tracks.", + "Participants in the main track were only allowed to use the provided training set, however, in the creative track, the use of external public sources was permitted.", + "In total, 113 teams submitted 1,228 runs to the main track; 33 teams submitted 239 runs to the creative track.", + "The highest performing team in the main track achieved an R-precision of 0.2241, an NDCG of 0.3946, and an average number of recommended songs clicks of 1.784.", + "In the creative track, an R-precision of 0.2233, an NDCG of 0.3939, and a click rate of 1.785 was obtained by the best team.", + "This article provides an overview of the challenge, including motivation, task definition, dataset description, and evaluation.", + "We further report and analyze the results obtained by the top-performing teams in each track and explore the approaches taken by the winners.", + "We finally summarize our key findings, discuss generalizability of approaches and results to domains other than music, and list the open avenues and possible future directions in the area of automatic playlist continuation." + ] + }, + { + "title": "SIGIR 2018 Workshop on Learning from Limited or Noisy Data for Information Retrieval", + "abstract": [ + "In recent years, machine learning approaches, and in particular deep neural networks, have yielded significant improvements on several natural language processing and computer vision tasks; however, such breakthroughs have not yet been observed in the area of information retrieval.", + "Besides the complexity of IR tasks, such as understanding the user's information needs, a main reason is the lack of high-quality and/or large-scale training data for many IR tasks.", + "This necessitates studying how to design and train machine learning algorithms where there is no large-scale or high-quality data in hand.", + "Therefore, considering the quick progress in development of machine learning models, this is an ideal time for a workshop that especially focuses on learning in such an important and challenging setting for IR tasks.", + "The goal of this workshop is to bring together researchers from industry---where data is plentiful but noisy---with researchers from academia---where data is sparse but clean to discuss solutions to these related problems." + ] + }, + { + "title": "Universal Approximation Functions for Fast Learning to Rank: Replacing Expensive Regression Forests with Simple Feed-Forward Networks", + "abstract": [ + "Learning to rank is a key component of modern information retrieval systems.", + "Recently, regression forest models (i.e., random forests, LambdaMART and gradient boosted regression trees) have come to dominate learning to rank systems in practice, as they provide the ability to learn from large scale data while generalizing well to additional test queries.", + "As a result, efficient implementations of these models is a concern in production systems, as evidenced by past work.", + "We propose an alternate method for optimizing the execution of learned models: converting these expensive ensembles to a feed-forward neural network.", + "This simple neural architecture is quite efficient to execute: we show that the resulting chain of matrix multiplies is quite efficient while maintaining the effectiveness of the original, more-expensive forest model.", + "Our neural approach has the advantage of being easier to train than any direct neural models, since it can match the previously-learned regression rather than learn to generalize relevance judgments directly.", + "We observe CPU document scoring speed improvements of up to 400x over traditional algorithms and up to 10x over state-of-the-art algorithms with no measurable loss in mean average precision.", + "With a GPU available, our algorithm is able to score every document in a batch in parallel for another 10-100x improvement.", + "While we are not the first work to observe that neural networks are efficient as well as being effective, our application of this observation to learning to rank is novel and will have large real-world impact." + ] + }, + { + "title": "On the Theory of Weak Supervision for Information Retrieval", + "abstract": [ + "Neural network approaches have recently shown to be effective in several information retrieval (IR) tasks.", + "However, neural approaches often require large volumes of training data to perform effectively, which is not always available.", + "To mitigate the shortage of labeled data, training neural IR models with weak supervision has been recently proposed and received considerable attention in the literature.", + "In weak supervision, an existing model automatically generates labels for a large set of unlabeled data, and a machine learning model is further trained on the generated \"weak\" data.", + "Surprisingly, it has been shown in prior art that the trained neural model can outperform the weak labeler by a significant margin.", + "Although these obtained improvements have been intuitively justified in previous work, the literature still lacks theoretical justification for the observed empirical findings.", + "In this paper, we provide a theoretical insight into weak supervision for information retrieval, focusing on learning to rank.", + "We model the weak supervision signal as a noisy channel that introduces noise to the correct ranking.", + "Based on the risk minimization framework, we prove that given some sufficient constraints on the loss function, weak supervision is equivalent to supervised learning under uniform noise.", + "We also find an upper bound for the empirical risk of weak supervision in case of non-uniform noise.", + "Following the recent work on using multiple weak supervision signals to learn more accurate models, we find an information theoretic lower bound on the number of weak supervision signals required to guarantee an upper bound for the pairwise error probability.", + "We empirically verify a set of presented theoretical findings, using synthetic and real weak supervision data." + ] + }, + { + "title": "Neural Matching Models for Question Retrieval and Next Question Prediction in Conversation", + "abstract": [ + "The recent boom of AI has seen the emergence of many human-computer conversation systems such as Google Assistant, Microsoft Cortana, Amazon Echo and Apple Siri.", + "We introduce and formalize the task of predicting questions in conversations, where the goal is to predict the new question that the user will ask, given the past conversational context.", + "This task can be modeled as a \"sequence matching\" problem, where two sequences are given and the aim is to learn a model that maps any pair of sequences to a matching probability.", + "Neural matching models, which adopt deep neural networks to learn sequence representations and matching scores, have attracted immense research interests of information retrieval and natural language processing communities.", + "In this paper, we first study neural matching models for the question retrieval task that has been widely explored in the literature, whereas the effectiveness of neural models for this task is relatively unstudied.", + "We further evaluate the neural matching models in the next question prediction task in conversations.", + "We have used the publicly available Quora data and Ubuntu chat logs in our experiments.", + "Our evaluations investigate the potential of neural matching models with representation learning for question retrieval and next question prediction in conversations.", + "Experimental results show that neural matching models perform well for both tasks." + ] + }, + { + "title": "RECSYS CHALLENGE 2018 : AUTOMATIC PLAYLIST CONTINUATION", + "abstract": [ + "In recent years, considerable attention has been given to studies on the role of playlists in music consumption.", + "A study carried out in 2016, by the Music Business Association [6], showed that playlists accounted for 31% of music listening time among listeners in the USA.", + "Another study, conducted by MIDiA [1], revealed that as many as 55% of streaming music service subscribers create playlists.", + "Accordingly, music streaming services such as Spotify currently host over 2 billion playlists [9].", + "This evidence may indicate the growing importance of playlists as a mode for music consumption, and indeed the crucial necessity of developing algorithms for automatic playlist continuation, which is the focus of the ACM Recommender Systems Challenge 2018 [7].", + "In this paper, we \u2014 the organization team of this challenge \u2014 briefly discuss the particular task we defined for the participating teams.", + "We also provide some information on the overall Challenge process.", + "ACM Recommender Systems Challenge The Recommender Systems Challenge is a yearly competition focusing on creating the best-performing recommendation approach for a specific task and a specific scenario.", + "From 2010 to 2017, the competition has drawn diverse participants from academia and industry [10,11,15].", + "Today, the Recommender Systems Challenge has become a key part of the ACM Conference on Recommender Systems series, the leading conference in recommender systems research.", + "The Recommender Systems Challenge has followed a similar structure since its inception: (1) a realworld problem is presented with a corresponding dataset, (2) researchers and developers form teams and sign up for participation, (3) participating teams submit their solutions prior to a deadline, (4) top participating teams submit papers that outline their approaches, (5) during a workshop at the ACM RecSys conference, accepted papers are presented and the winning teams are announced.", + "c \u00a9 Markus Schedl, Hamed Zamani, Ching-Wei Chen, Yashar Deldjoo, Mehdi Elahi.", + "Licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).", + "Attribution: Markus Schedl, Hamed Zamani, Ching-Wei Chen, Yashar Deldjoo, Mehdi Elahi. \u201c", + "RecSys Challenge 2018: Automatic Playlist Continuation\u201d, 18th International Society for Music Information Retrieval Conference, Suzhou, China, 2017.", + "In MIREX, a few attempts to launch music recommendation [3] or personalized radio stationing [4] tasks were performed in the past, but they were never realized to the best of the authors\u2019 knowledge.", + "In comparison, by organizing the task in 2018 at the ACM Recommender Systems conference, we will reach a broader audience and with the full support of a major music streaming company, Spotify, we are sure to attract a remarkable number of participants.", + "The MIREX task probably closest to ours is the Audio Music Similarity and Retrieval task [5], which has been run in 2016 for the last time.", + "However, the organizers explicitly state that the task is \u201cnot playlist generation or music recommendation\u201d, rather pure similarity aspects.", + "Another related challenge was the Million Song Dataset Challenge [2], which featured a traditional recommendation task: based on a part of the user\u2019s listening history, another, withheld part needed to be predicted.", + "In contrast, our task explicitly considers hand-curated playlists, not listening histories.", + "Automatic Playlist Continuation The task for the Recommender Systems Challenge in 2018 will be automatic playlist continuation (APC).", + "This task consists of adding one or more tracks to a music playlist (of arbitrary length) in a way that fits the target characteristics of the original playlist [12,16].", + "APC is a useful feature for music streaming services not only because it can extend listening session length, but also because it can increase engagement of users on their platform by making it easier for users to create playlists that they can enjoy and share.", + "As part of this challenge, Spotify will be releasing a public dataset of roughly 1 million user-created playlists.", + "The dataset will include the title of each playlist, as well as the list of tracks, and some associated metadata, for each playlist.", + "A separate evaluation set will consist of a set of playlists from which a number of tracks have been withheld.", + "The task will then be to predict the missing tracks in those playlists, and participating teams will be required to submit their predictions for those missing tracks.", + "An appropriate accuracy metric will be defined, which will then be used to evaluate the performance of each of the submissions.", + "The dataset and associated evaluation metrics are scheduled to be released by the end of 2017.", + "Up-to-date information can be found on the Challenge website.", + "1 1 http://2018.recsyschallenge.com" + ] + }, + { + "title": "Neural Ranking Models with Multiple Document Fields", + "abstract": [ + "Deep neural networks have recently shown promise in the ad-hoc retrieval task.", + "However, such models have often been based on one field of the document, for example considering document title only or document body only.", + "Since in practice documents typically have multiple fields, and given that non-neural ranking models such as BM25F have been developed to take advantage of document structure, this paper investigates how neural models can deal with multiple document fields.", + "We introduce a model that can consume short text fields such as document title and long text fields such as document body.", + "It can also handle multi-instance fields with variable number of instances, for example where each document has zero or more instances of incoming anchor text.", + "Since fields vary in coverage and quality, we introduce a masking method to handle missing field instances, as well as a field-level dropout method to avoid relying too much on any one field.", + "As in the studies of non-neural field weighting, we find it is better for the ranker to score the whole document jointly, rather than generate a per-field score and aggregate.", + "We find that different document fields may match different aspects of the query and therefore benefit from comparing with separate representations of the query text.", + "The combination of techniques introduced here leads to a neural ranker that can take advantage of full document structure, including multiple instance and missing instance data, of variable length.", + "The techniques significantly enhance the performance of the ranker, and outperform a learning to rank baseline with hand-crafted features." + ] + }, + { + "title": "A Semantic-Aware Profile Updating Model for Text Recommendation", + "abstract": [ + "Content-based recommender systems (CBRSs) rely on user-item similarities that are calculated between user profiles and item representations.", + "Appropriate representation of each user profile based on the user's past preferences can have a great impact on user's satisfaction in CBRSs.", + "In this paper, we focus on text recommendation and propose a novel profile updating model based on previously recommended items as well as semantic similarity of terms calculated using distributed representation of words.", + "We evaluate our model using two standard text recommendation datasets: TREC-9 Filtering Track and CLEF 2008-09 INFILE Track collections.", + "Our experiments investigate the importance of both past recommended items and semantic similarities in recommendation performance.", + "The proposed profile updating method significantly outperforms the baselines, which confirms the importance of incorporating semantic similarities in the profile updating task." + ] + }, + { + "title": "Term Proximity Constraints for Pseudo-Relevance Feedback", + "abstract": [ + "Pseudo-relevance feedback (PRF) refers to a query expansion strategy based on top-retrieved documents, which has been shown to be highly effective in many retrieval models.", + "Previous work has introduced a set of constraints (axioms) that should be satisfied by any PRF model.", + "In this paper, we propose three additional constraints based on the proximity of feedback terms to the query terms in the feedback documents.", + "As a case study, we consider the log-logistic model, a state-of-the-art PRF model that has been proven to be a successful method in satisfying the existing PRF constraints, and show that it does not satisfy the proposed constraints.", + "We further modify the log-logistic model based on the proposed proximity-based constraints.", + "Experiments on four TREC collections demonstrate the effectiveness of the proposed constraints.", + "Our modification the log-logistic model leads to significant and substantial (up to 15%) improvements.", + "Furthermore, we show that the proposed proximity-based function outperforms the well-known Gaussian kernel which does not satisfy all the proposed constraints." + ] + }, + { + "title": "Neural Ranking Models with Weak Supervision", + "abstract": [ + "Learning state-of-the-art deep neural network models requires a large amounts of labeled data, which is not always readily available and can be expensive to obtain.", + "To circumvent the lack of human-labeled training examples, unsupervised learning methods aim to model the underlying data distribution, thus learning powerful feature representations of the input data, which can be helpful for building more accurate discriminative models especially when little or even no supervised data is available.", + "A large group of unsupervised neural models seeks to exploit the implicit internal structure of the input data, which in turn requires customized formulation of the training objective (loss function), targeted network architectures and often non-trivial training setups.", + "Despite the advances in computer vision, speech recognition, and NLP tasks using unsupervised deep neural networks, such advances have not been observed in core information retrieval (IR) problems, such as ranking.", + "A plausible explanation is the complexity of the ranking problem in IR, in the sense that it is not obvious how to learn a ranking model from queries and documents when no supervision in form of the relevance information is available.", + "To overcome this issue, in this paper, we propose to leverage large amounts of unsupervised data to infer \u201cnoisy\u201d or \u201cweak\u201d labels and use that signal for learning supervised models as if we had the ground truth labels.", + "In particular, we use classic unsupervised IR models as a weak supervision signal for training deep neural ranking models.", + "Weak supervision here refers to a learning approach that creates its own training data by heuristically retrieving documents for a large query set.", + "This training data is created automatically, and thus it is possible to generate billions of training instances with almost no cost.", + "As training deep neural networks is an exceptionally data hungry process, the idea of" + ] + }, + { + "title": "UMass at TREC 2017 Common Core Track", + "abstract": [ + "This is an overview of University of Massachusetts efforts in providing document retrieval run submissions for the TREC Common Core Track with the goal of using newly developed techniques in retrieval and ranking to provide many new documents for relevance judgments.", + "It is hoped these new techniques will reveal new documents not seen via traditional techniques, that will increase the numbers of relevant judged documents for the research collection." + ] + }, + { + "title": "Relevance-based Word Embedding", + "abstract": [ + "Learning a high-dimensional dense representation for vocabulary terms, also known as a word embedding, has recently attracted much attention in natural language processing and information retrieval tasks.", + "The embedding vectors are typically learned based on term proximity in a large corpus.", + "This means that the objective in well-known word embedding algorithms, e.g., word2vec, is to accurately predict adjacent word(s) for a given word or context.", + "However, this objective is not necessarily equivalent to the goal of many information retrieval (IR) tasks.", + "The primary objective in various IR tasks is to capture relevance instead of term proximity, syntactic, or even semantic similarity.", + "This is the motivation for developing unsupervised relevance-based word embedding models that learn word representations based on query-document relevance information.", + "In this paper, we propose two learning models with different objective functions; one learns a relevance distribution over the vocabulary set for each query, and the other classifies each term as belonging to the relevant or non-relevant class for each query.", + "To train our models, we used over six million unique queries and the top ranked documents retrieved in response to each query, which are assumed to be relevant to the query.", + "We extrinsically evaluate our learned word representation models using two IR tasks: query expansion and query classification.", + "Both query expansion experiments on four TREC collections and query classification experiments on the KDD Cup 2005 dataset suggest that the relevance-based word embedding models significantly outperform state-of-the-art proximity-based embedding models, such as word2vec and GloVe." + ] + }, + { + "title": "Situational Context for Ranking in Personal Search", + "abstract": [ + "Modern search engines leverage a variety of sources, beyond the conventional query-document content similarity, to improve their ranking performance.", + "Among them, query context has attracted attention in prior work.", + "Previously, query context was mainly modeled by user search history, either long-term or short-term, to help the ranking of future queries.", + "In this paper, we focus on situational context, i.e., the contextual features of the current search request that are independent from both query content and user history.", + "As an example, situational context can depend on search request time and location.", + "We propose two context-aware ranking models based on neural networks.", + "The first model learns a low-dimensional deep representation from the combination of contextual features.", + "The second model extends the first one by leveraging binarized contextual features in addition to the high-level abstractions learned using a deep network.", + "The existing context-aware ranking models are mainly based on search history, especially click data that can be gathered from the search engine logs.", + "Although context-aware models have been widely explored in web search, their influence on search scenarios where click data is highly sparse is relatively unstudied.", + "The focus of this paper, personal search (e.g., email search or on-device search), is one of such scenarios.", + "We evaluate our models using the click data collected from one of the world's largest personal search engines.", + "The experiments demonstrate that the proposed models significantly outperform the baselines which do not take context into account.", + "These results indicate the importance of situational context for personal search, and open up a venue for further exploration of situational context in other search scenarios." + ] + }, + { + "title": "Neural Ranking Models with Weak Supervision", + "abstract": [ + "Despite the impressive improvements achieved by unsupervised deep neural networks in computer vision and NLP tasks, such improvements have not yet been observed in ranking for information retrieval.", + "The reason may be the complexity of the ranking problem, as it is not obvious how to learn from queries and documents when no supervised signal is available.", + "Hence, in this paper, we propose to train a neural ranking model using weak supervision, where labels are obtained automatically without human annotators or any external resources (e.g., click data).", + "To this aim, we use the output of an unsupervised ranking model, such as BM25, as a weak supervision signal.", + "We further train a set of simple yet effective ranking models based on feed-forward neural networks.", + "We study their effectiveness under various learning scenarios (point-wise and pair-wise models) and using different input representations (i.e., from encoding query-document pairs into dense/sparse vectors to using word embedding representation).", + "We train our networks using tens of millions of training instances and evaluate it on two standard collections: a homogeneous news collection (Robust) and a heterogeneous large-scale web collection (ClueWeb).", + "Our experiments indicate that employing proper objective functions and letting the networks to learn the input representation based on weakly supervised data leads to impressive performance, with over 13% and 35% MAP improvements over the BM25 model on the Robust and the ClueWeb collections.", + "Our findings also suggest that supervised neural ranking models can greatly benefit from pre-training on large amounts of weakly labeled data that can be easily obtained from unsupervised IR models." + ] + }, + { + "title": "Improving Retrieval Performance for Verbose Queries via Axiomatic Analysis of Term Discrimination Heuristic", + "abstract": [ + "Number of terms in a query is a query-specific constant that is typically ignored in retrieval functions.", + "However, previous studies have shown that the performance of retrieval models varies for different query lengths, and it usually degrades when query length increases.", + "A possible reason for this issue can be the extraneous terms in longer queries that makes it a challenge for the retrieval models to distinguish between the key and complementary concepts of the query.", + "As a signal to understand the importance of a term, inverse document frequency (IDF) can be used to discriminate query terms.", + "In this paper, we propose a constraint to model the interaction between query length and IDF.", + "Our theoretical analysis shows that current state-of-the-art retrieval models, such as BM25, do not satisfy the proposed constraint.", + "We further analyze the BM25 model and suggest a modification to adapt BM25 so that it adheres to the new constraint.", + "Our experiments on three TREC collections demonstrate that the proposed modification outperforms the baselines, especially for verbose queries." + ] + }, + { + "title": "Word Embedding Causes Topic Shifting; Exploit Global Context!", + "abstract": [ + "Exploitation of term relatedness provided by word embedding has gained considerable attention in recent IR literature.", + "However, an emerging question is whether this sort of relatedness fits to the needs of IR with respect to retrieval effectiveness.", + "While we observe a high potential of word embedding as a resource for related terms, the incidence of several cases of topic shifting deteriorates the final performance of the applied retrieval models.", + "To address this issue, we revisit the use of global context (i.e. the term co-occurrence in documents) to measure the term relatedness.", + "We hypothesize that in order to avoid topic shifting among the terms with high word embedding similarity, they should often share similar global contexts as well.", + "We therefore study the effectiveness of post filtering of related terms by various global context relatedness measures.", + "Experimental results show significant improvements in two out of three test collections, and support our initial hypothesis regarding the importance of considering global context in retrieval." + ] + }, + { + "title": "Neural Ranking Models with Weak Supervision", + "abstract": [ + "Learning state-of-the-art deep neural network models requires a large amounts of labeled data, which is not always readily available and can be expensive to obtain.", + "To circumvent the lack of human-labeled training examples, unsupervised learning methods aim to model the underlying data distribution, thus learning powerful feature representations of the input data, which can be helpful for building more accurate discriminative models especially when little or even no supervised data is available.", + "A large group of unsupervised neural models seeks to exploit the implicit internal structure of the input data, which in turn requires customized formulation of the training objective (loss function), targeted network architectures and often non-trivial training setups.", + "Despite the advances in computer vision, speech recognition, and NLP tasks using unsupervised deep neural networks, such advances have not been observed in core information retrieval (IR) problems, such as ranking.", + "A plausible explanation is the complexity of the ranking problem in IR, in the sense that it is not obvious how to learn a ranking model from queries and documents when no supervision in form of the relevance information is available.", + "To overcome this issue, in this paper, we propose to leverage large amounts of unsupervised data to infer \u201cnoisy\u201d or \u201cweak\u201d labels and use that signal for learning supervised models as if we had the ground truth labels.", + "In particular, we use classic unsupervised IR models as a weak supervision signal for training deep neural ranking models.", + "Weak supervision here refers to a learning approach that creates its own training data by heuristically retrieving documents for a large query set.", + "This training data is created automatically, and thus it is possible to generate billions of training instances with almost no cost.", + "As training deep neural networks is an exceptionally data hungry process, the idea of" + ] + }, + { + "title": "Estimating Embedding Vectors for Queries", + "abstract": [ + "The dense vector representation of vocabulary terms, also known as word embeddings, have been shown to be highly effective in many natural language processing tasks.", + "Word embeddings have recently begun to be studied in a number of information retrieval (IR) tasks.", + "One of the main steps in leveraging word embeddings for IR tasks is to estimate the embedding vectors of queries.", + "This is a challenging task, since queries are not always available during the training phase of word embedding vectors.", + "Previous work has considered the average or sum of embedding vectors of all query terms (AWE) to model the query embedding vectors, but no theoretical justification has been presented for such a model.", + "In this paper, we propose a theoretical framework for estimating query embedding vectors based on the individual embedding vectors of vocabulary terms.", + "We then provide a number of different implementations of this framework and show that the AWE method is a special case of the proposed framework.", + "We also introduce pseudo query vectors, the query embedding vectors estimated using pseudo-relevant documents.", + "We further extrinsically evaluate the proposed methods using two well-known IR tasks: query expansion and query classification.", + "The estimated query embedding vectors are evaluated via query expansion experiments over three newswire and web TREC collections as well as query classification experiments over the KDD Cup 2005 test set.", + "The experiments show that the introduced pseudo query vectors significantly outperform the AWE method." + ] + }, + { + "title": "Pseudo-Relevance Feedback Based on Matrix Factorization", + "abstract": [ + "In information retrieval, pseudo-relevance feedback (PRF) refers to a strategy for updating the query model using the top retrieved documents.", + "PRF has been proven to be highly effective in improving the retrieval performance.", + "In this paper, we look at the PRF task as a recommendation problem: the goal is to recommend a number of terms for a given query along with weights, such that the final weights of terms in the updated query model better reflect the terms' contributions in the query.", + "To do so, we propose RFMF, a PRF framework based on matrix factorization which is a state-of-the-art technique in collaborative recommender systems.", + "Our purpose is to predict the weight of terms that have not appeared in the query and matrix factorization techniques are used to predict these weights.", + "In RFMF, we first create a matrix whose elements are computed using a weight function that shows how much a term discriminates the query or the top retrieved documents from the collection.", + "Then, we re-estimate the created matrix using a matrix factorization technique.", + "Finally, the query model is updated using the re-estimated matrix.", + "RFMF is a general framework that can be employed with any retrieval model.", + "In this paper, we implement this framework for two widely used document retrieval frameworks: language modeling and the vector space model.", + "Extensive experiments over several TREC collections demonstrate that the RFMF framework significantly outperforms competitive baselines.", + "These results indicate the potential of using other recommendation techniques in this task." + ] + }, + { + "title": "Embedding-based Query Language Models", + "abstract": [ + "Word embeddings, which are low-dimensional vector representations of vocabulary terms that capture the semantic similarity between them, have recently been shown to achieve impressive performance in many natural language processing tasks.", + "The use of word embeddings in information retrieval, however, has only begun to be studied.", + "In this paper, we explore the use of word embeddings to enhance the accuracy of query language models in the ad-hoc retrieval task.", + "To this end, we propose to use word embeddings to incorporate and weight terms that do not occur in the query, but are semantically related to the query terms.", + "We describe two embedding-based query expansion models with different assumptions.", + "Since pseudo-relevance feedback methods that use the top retrieved documents to update the original query model are well-known to be effective, we also develop an embedding-based relevance model, an extension of the effective and robust relevance model approach.", + "In these models, we transform the similarity values obtained by the widely-used cosine similarity with a sigmoid function to have more discriminative semantic similarity values.", + "We evaluate our proposed methods using three TREC newswire and web collections.", + "The experimental results demonstrate that the embedding-based methods significantly outperform competitive baselines in most cases.", + "The embedding-based methods are also shown to be more robust than the baselines." + ] + }, + { + "title": "Axiomatic Analysis for Improving the Log-Logistic Feedback Model", + "abstract": [ + "Pseudo-relevance feedback (PRF) has been proven to be an effective query expansion strategy to improve retrieval performance.", + "Several PRF methods have so far been proposed for many retrieval models.", + "Recent theoretical studies of PRF methods show that most of the PRF methods do not satisfy all necessary constraints.", + "Among all, the log-logistic model has been shown to be an effective method that satisfies most of the PRF constraints.", + "In this paper, we first introduce two new PRF constraints.", + "We further analyze the log-logistic feedback model and show that it does not satisfy these two constraints as well as the previously proposed \"relevance effect\" constraint.", + "We then modify the log-logistic formulation to satisfy all these constraints.", + "Experiments on three TREC newswire and web collections demonstrate that the proposed modification significantly outperforms the original log-logistic model, in all collections." + ] + }, + { + "title": "Reference-free and Confidence-independent Binary Quality Estimation for Automatic Speech Recognition", + "abstract": [ + "English.", + "We address the problem of assigning binary quality labels to automatically transcribed utterances when neither reference transcripts nor information about the decoding process are accessible.", + "Our quality estimation models are evaluated in a large vocabulary continuous speech recognition setting (the transcription of English TED talks).", + "In this setting, we apply different learning algorithms and strategies and measure performance in two testing conditions characterized by different distributions of \u201cgood\u201d and \u201cbad\u201d instances.", + "The positive results of our experiments pave the way towards the use of binary estimators of ASR output quality in a number of application scenarios." + ] + }, + { + "title": "Adaptive User Engagement Evaluation via Multi-task Learning", + "abstract": [ + "User engagement evaluation task in social networks has recently attracted considerable attention due to its applications in recommender systems.", + "In this task, the posts containing users' opinions about items, e.g., the tweets containing the users' ratings about movies in the IMDb website, are studied.", + "In this paper, we try to make use of tweets from different web applications to improve the user engagement evaluation performance.", + "To this aim, we propose an adaptive method based on multi-task learning.", + "Since in this paper we study the problem of detecting tweets with positive engagement which is a highly imbalanced classification problem, we modify the loss function of multi-task learning algorithms to cope with the imbalanced data.", + "Our evaluations over a dataset including the tweets of four diverse and popular data sources, i.e., IMDb, YouTube, Goodreads, and Pandora, demonstrate the effectiveness of the proposed method.", + "Our findings suggest that transferring knowledge between data sources can improve the user engagement evaluation performance." + ] + }, + { + "title": "Multitask Learning for Adaptive Quality Estimation of Automatically Transcribed Utterances", + "abstract": [ + "We investigate the problem of predicting the quality of automatic speech recognition (ASR) output under the following rigid constraints: i) reference transcriptions are not available, ii) confidence information about the system that produced the transcriptions is not accessible, and iii) training and test data come from multiple domains.", + "To cope with these constraints (typical of the constantly increasing amount of automatic transcriptions that can be found on the Web), we propose a domain-adaptive approach based on multitask learning.", + "Different algorithms and strategies are evaluated with English data coming from four domains, showing that the proposed approach can cope with the limitations of previously proposed single task learning methods." + ] + }, + { + "title": "Expanded N-Grams for Semantic Text Alignment Notebook for PAN at CLEF 2014", + "abstract": [ + "Text alignment is a sub-task in the plagiarism detection process.", + "In this paper we discuss our approach to address this problem.", + "Our approach is based on mapping text alignment to the problem of subsequence matching just as previous works.", + "We have prepared a framework, which lets us combine different feature types and different strategies for merging the features.", + "We have proposed two different solutions to relax the comparison of two documents, so as to consider the semantic relations between them.", + "Our first approach is based on defining a new feature type that contains semantic information about its corresponding doc- ument.", + "In our second approach we have proposed a new method for comparing the features considering their semantic relations.", + "Finally, We have applied DB- SCAN clustering algorithm to merge features in a neighborhood in both source and suspicious documents.", + "Our experiments indicate that different feature sets are suitable for detecting different types of plagiarism." + ] + }, + { + "title": "Regression and Learning to Rank Aggregation for User Engagement Evaluation", + "abstract": [ + "User engagement refers to the amount of interaction an instance (e.g., tweet, news, and forum post) achieves.", + "Ranking the items in social media websites based on the amount of user participation in them, can be used in different applications, such as recommender systems.", + "In this paper, we consider a tweet containing a rating for a movie as an instance and focus on ranking the instances of each user based on their engagement, i.e., the total number of retweets and favorites it will gain.", + "\n For this task, we define several features which can be extracted from the meta-data of each tweet.", + "The features are partitioned into three categories: user-based, movie-based, and tweet-based.", + "We show that in order to obtain good results, features from all categories should be considered.", + "We exploit regression and learning to rank methods to rank the tweets and propose to aggregate the results of regression and learning to rank methods to achieve better performance.", + "\n We have run our experiments on an extended version of MovieTweeting dataset provided by ACM RecSys Challenge 2014.", + "The results show that learning to rank approach outperforms most of the regression models and the combination can improve the performance significantly." ] } ], "user_kps": [ - "argumentation mining", - "attention-based neural machine translation", "cone beam computed tomography", + "context-aware query suggestion", "conversational interactivity", "conversational interfaces", - "dialogue systems", - "discriminative language modeling", + "conversational systems", + "document retrieval", "exploratory search tasks", - "faceted search", - "learning concepts", + "information retrieval models", + "mobile search", "neural ranking models", - "question answering", + "pseudo-relevance feedback", + "query retrieval", "radiation dose", "ranked retrieval", + "relevance feedback technique", + "relevance networks", "retrieval model", "retrieval tasks", - "similarity-based retrieval", - "term networks", - "therapeutic targets", + "visual question answering", "word retrieval" ] } \ No newline at end of file