A multilingual collection may contain useful knowledge in other languages to supplement and correct the facts in the original language for Retrieval-Augmented Generation (RAG). However, the vanilla approach that simply concatenates multiple pieces of knowledge from different languages into the context may fail to improve effectiveness due to the potential disparities across languages. To better leverage multilingual knowledge, we propose CroSearch-R1, a search-augmented reinforcement learning framework to integrate multilingual knowledge into the Group Relative Policy Optimization (GRPO) process. In particular, the approach adopts a multi-turn retrieval strategy with cross-lingual knowledge integration to dynamically align the knowledge from other languages as supplementary evidence into a unified representation space. Furthermore, we introduce a multilingual rollout mechanism to optimize reasoning transferability across languages. Experimental results demonstrate that our framework effectively leverages cross-lingual complementarity and improves the effectiveness of RAG with multilingual collections.

Large Language Models (LLMs) have recently been explored as fine-grained zero-shot re-rankers by leveraging attention signals to estimate document relevance. However, existing methods either aggregate attention signals across all heads or rely on a statically selected subset identified by heuristic rules. This solution can be suboptimal because the informative heads can vary across queries or domains. Moreover, naively combining multiple heads can degrade performance due to redundancy or conflicting ranking signals. In this paper, we propose a query-dependent head selection method, RouteHead, for attention-based re-ranking with LLMs. Specifically, we learn a lightweight router that can map each query to an optimal head set, and relevance scores are computed by aggregating attention signals only from these heads. Since query-to-head optimal labels are unavailable, we first construct pseudo labels via an offline search. The router represents each head with a learnable embedding and represents each query using an embedding extracted from the hidden states of the frozen LLM. Then it is trained on the pseudo labels with a sparsity regularizer. Experiments on diverse benchmarks and multiple LLM backbones show that the proposed method consistently outperforms strong baselines.

Most recommendation benchmarks evaluate how well a model imitates user behavior. In financial advisory, however, observed actions can be noisy or short-sighted under market volatility and may conflict with a user's long-term goals. Treating what users chose as the sole ground truth, therefore, conflates behavioral imitation with decision quality. We introduce Conv-FinRe, a conversational and longitudinal benchmark for stock recommendation that evaluates LLMs beyond behavior matching. Given an onboarding interview, step-wise market context, and advisory dialogues, models must generate rankings over a fixed investment horizon. Crucially, Conv-FinRe provides multi-view references that distinguish descriptive behavior from normative utility grounded in investor-specific risk preferences, enabling diagnosis of whether an LLM follows rational analysis, mimics user noise, or is driven by market momentum. We build the benchmark from real market data and human decision trajectories, instantiate controlled advisory conversations, and evaluate a suite of state-of-the-art LLMs. Results reveal a persistent tension between rational decision quality and behavioral alignment: models that perform well on utility-based ranking often fail to match user choices, whereas behaviorally aligned models can overfit short-term noise. The dataset is publicly released on Hugging Face. https://huggingface.co/collections/TheFinAI/conv-finre, and the codebase is available on GitHub. https://github.com/The-FinAI/Conv-FinRe.

Going beyond simple text processing, financial auditing requires detecting semantic, structural, and numerical inconsistencies across large-scale disclosures. As financial reports are filed in XBRL, a structured XML format governed by accounting standards, auditing becomes a structured information extraction and reasoning problem involving concept alignment, taxonomy-defined relations, and cross-document consistency. Although large language models (LLMs) show promise on isolated financial tasks, their capability in professional-grade auditing remains unclear. We introduce FinAuditing, a taxonomy-aligned, structure-aware benchmark built from real XBRL filings. It contains 1,102 annotated instances averaging over 33k tokens and defines three tasks: Financial Semantic Matching (FinSM), Financial Relationship Extraction (FinRE), and Financial Mathematical Reasoning (FinMR). Evaluations of 13 state-of-the-art LLMs reveal substantial gaps in concept retrieval, taxonomy-aware relation modeling, and consistent cross-document reasoning. These findings highlight the need for realistic, structure-aware benchmarks. We release the evaluation code1 and dataset2 publicly, and the task currently serves as the official benchmark of an ongoing public evaluation contest3.

The development of large language models (LLMs) has achieved superior performance in a range of downstream tasks, including LLM-based retrieval-augmented generation (RAG). The quality of generated content heavily relies on the usefulness of the retrieved information and the capacity of LLMs' internal information processing mechanism to incorporate it in answer generation. It is generally assumed that the retrieved information is relevant to the question. However, the retrieved information may have a variable degree of relevance and usefulness, depending on the question and the document collection. It is important to take into account the relevance of the retrieved information in answer generation. In this paper, we propose OpenDecoder, a new approach that leverages explicit evaluation of the retrieved information as quality indicator features for generation. We aim to build a RAG model that is more robust to varying levels of noisy context. Three types of explicit evaluation information are considered: relevance score, ranking score, and QPP (query performance prediction) score. The experimental results on five benchmark datasets demonstrate the effectiveness and better robustness of OpenDecoder by outperforming various baseline methods. Importantly, this paradigm is flexible to be integrated with the post-training of LLMs for any purposes and incorporated with any type of external indicators.

Multi-turn interactions between users and information-seeking systems have become a popular paradigm to satisfy complex information needs via a flexible interface and context understanding capacity. However, existing methods primarily adapt single-turn retrieval-augmented generation (RAG) pipelines to conversational settings without effectively incorporating historical information, such as previous search results, turn dependency, and historical evidence grounding. To effectively manage and utilize the information in conversations, we explore the feasibility of boosting response generation by leveraging historical information and propose several strategies to incorporate this information individually or in combination. We conduct experiments on three widely used conversational search benchmarks, each containing thousands of samples. Our method consistently outperforms previous strong baselines across different settings, achieving approximately a 10% absolute improvement over the second-best approach. Besides, our analyses help to understand the behind-the-scenes behavior of our methods. • We investigate the feasibility of leveraging abundant historical information to improve RAG performance in conversations. • We design several training-free strategies from different aspects, that can be used individually or in combination to boost RAG performance. • We conduct thorough experiments on three datasets to demonstrate the effectiveness of our methods, and analyze the potential paradigms behind the model.

Conversational search enables multi-turn interactions between users and systems to fulfill users' complex information needs. During this interaction, the system should understand the users' search intent within the conversational context and then return the relevant information through a flexible, dialogue-based interface. The recent powerful large language models (LLMs) with capacities of instruction following, content generation, and reasoning, attract significant attention and advancements, providing new opportunities and challenges for building up intelligent conversational search systems. This tutorial aims to introduce the connection between fundamentals and the emerging topics revolutionized by LLMs in the context of conversational search. It is designed for students, researchers, and practitioners from both academia and industry. Participants will gain a comprehensive understanding of both the core principles and cutting-edge developments driven by LLMs in conversational search, equipping them with the knowledge needed to contribute to the development of next-generation conversational search systems.

A key challenge in personalized product search is to capture user’s preferences. Recent work attempted to model sequences of user historical behaviors, i.e., product purchase histories, to build user profiles and to personalize results accordingly. Although these approaches have demonstrated promising retrieval performances, we notice that most of them focus solely on the intra-sequence interactions between items. However, as there is usually a small amount of historical behavior data, the user profiles learned by these approaches could be very sensitive to the noise included in it. To tackle this problem, we propose incorporating out-of-sequence external information to enhance user modeling. More specifically, we inject the external item–item relations (e.g., belonging to the same brand), and query–query relations (e.g., the semantic similarities between them), into the intra-sequence interaction to learn better user profiles. In addition, we devise two auxiliary decoders, with the historical item sequence reconstruction task and the global item similarity prediction task, to further improve the reliability of user modeling. Experimental results on two datasets from simulated and real user search logs respectively show that the proposed personalized product search method outperforms existing approaches.

As a cornerstone of modern information access, search engines have become indispensable in everyday life. With the rapid advancements in AI and natural language processing (NLP) technologies, particularly large language models (LLMs), search engines have evolved to support more intuitive and intelligent interactions between users and systems. Conversational search, an emerging paradigm for next-generation search engines, leverages natural language dialogue to facilitate complex and precise information retrieval, thus attracting significant attention. Unlike traditional keyword-based search engines, conversational search systems enhance user experience by supporting intricate queries, maintaining context over multi-turn interactions, and providing robust information integration and processing capabilities. Key components such as query reformulation, search clarification, conversational retrieval, and response generation work in unison to enable these sophisticated interactions. In this survey, we explore the recent advancements and potential future directions in conversational search, examining the critical modules that constitute a conversational search system. We highlight the integration of LLMs in enhancing these systems and discuss the challenges and opportunities that lie ahead in this dynamic field. Additionally, we provide insights into real-world applications and robust evaluations of current conversational search systems, aiming to guide future research and development in conversational search.

Conversational search supports multi-turn user-system interactions to solve complex information needs. Different from the traditional single-turn ad-hoc search, conversational search encounters a more challenging problem of context-dependent query understanding with the lengthy and long-tail conversational history context. While conversational query rewriting (CQR) methods leverage explicit rewritten queries to train a rewriting model to transform the context-dependent query into a stand-stone search query, this is usually done without considering the quality of search results. Conversational dense retrieval (CDR) methods use fine-tuning to improve a pre-trained ad-hoc query encoder, but they are limited by the conversational search data available for training. In this paper, we leverage both rewritten queries and relevance judgments in the conversational search data to train a better query representation model. The key idea is to align the query representation with those of rewritten queries and relevant documents. The proposed model -- Query Representation Alignment Conversational Dense Retriever, QRACDR, is tested on eight datasets, including various settings in conversational search and ad-hoc search. The results demonstrate the strong performance of QRACDR compared with other state-of-the-art methods, and confirm the effectiveness of representation alignment.

Personalized conversational information retrieval (CIR) combines conversational and personalizable elements to satisfy various users' complex information needs through multi-turn interaction based on their backgrounds. The key promise is that the personal textual knowledge base (PTKB) can improve the CIR effectiveness because the retrieval results can be more related to the user's background. However, PTKB is noisy: not every piece of knowledge in PTKB is relevant to the specific query at hand. In this paper, we explore and test several ways to select knowledge from PTKB and use it for query reformulation by using a large language model (LLM). The experimental results show the PTKB might not always improve the search results when used alone, but LLM can help generate a more appropriate personalized query when high-quality guidance is provided.

Graph-based models and contrastive learning have emerged as prominent methods in Collaborative Filtering (CF). While many existing models in CF incorporate these methods in their design, there seems to be a limited depth of analysis regarding the foundational principles behind them. This paper bridges graph convolution, a pivotal element of graph-based models, with contrastive learning through a theoretical framework. By examining the learning dynamics and equilibrium of the contrastive loss, we offer a fresh lens to understand contrastive learning via graph theory, emphasizing its capability to capture high-order connectivity. Building on this analysis, we further show that the graph convolutional layers often used in graph-based models are not essential for high-order connectivity modeling and might contribute to the risk of oversmoothing. Stemming from our findings, we introduce Simple Contrastive Collaborative Filtering (SCCF), a simple and effective algorithm based on a naive embedding model and a modified contrastive loss. The efficacy of the algorithm is demonstrated through extensive experiments across four public datasets. The experiment code is available at https://github.com/wu1hong/SCCF.

We introduce C-Pack, a package of resources that significantly advances the field of general text embeddings for Chinese. C-Pack includes three critical resources. 1) C-MTP is a massive training dataset for text embedding, which is based on the curation of vast unlabeled corpora and the integration of high-quality labeled corpora. 2) C-MTEB is a comprehensive benchmark for Chinese text embeddings covering 6 tasks and 35 datasets. 3) BGE is a family of embedding models covering multiple sizes. Our models outperform all prior Chinese text embeddings on C-MTEB by more than +10% upon the time of the release. We also integrate and optimize the entire suite of training methods for BGE. Along with our resources on general Chinese embedding, we release our data and models for English text embeddings. The English models also achieve state-of-the-art performance on the MTEB benchmark; meanwhile, our released English data is 2 times larger than the Chinese data. Both Chinese and English datasets are the largest public release of training data for text embeddings. All these resources are made publicly available at https://github.com/FlagOpen/FlagEmbedding.

Modern recommender systems employ various sequential modules such as self-attention to learn dynamic user interests. However, these methods are less effective in capturing collaborative and transitional signals within user interaction sequences. First, the self-attention architecture uses the embedding of a single item as the attention query, making it challenging to capture collaborative signals. Second, these methods typically follow an auto-regressive framework, which is unable to learn global item transition patterns. To overcome these limitations, we propose a new method called Multi-Query Self-Attention with Transition-Aware Embedding Distillation (MQSA-TED). First, we propose an L-query self-attention module that employs flexible window sizes for attention queries to capture collaborative signals. In addition, we introduce a multi-query self-attention method that balances the bias-variance trade-off in modeling user preferences by combining long and short-query self-attentions. Second, we develop a transition-aware embedding distillation module that distills global item-to-item transition patterns into item embeddings, which enables the model to memorize and leverage transitional signals and serves as a calibrator for collaborative signals. Experimental results on four real-world datasets demonstrate the effectiveness of the proposed modules.

Retrieval-augmented generation have become central in natural language processing due to their efficacy in generating factual content. While traditional methods employ single-time retrieval, more recent approaches have shifted towards multi-time retrieval for multi-hop reasoning tasks. However, these strategies are bound by predefined reasoning steps, potentially leading to inaccuracies in response generation. This paper introduces MetaRAG, an approach that combines the retrieval-augmented generation process with metacognition. Drawing from cognitive psychology, metacognition allows an entity to self-reflect and critically evaluate its cognitive processes. By integrating this, MetaRAG enables the model to monitor, evaluate, and plan its response strategies, enhancing its introspective reasoning abilities. Through a three-step metacognitive regulation pipeline, the model can identify inadequacies in initial cognitive responses and fixes them. Empirical evaluations show that MetaRAG significantly outperforms existing methods.

Personalized search and search result diversification are two possible solutions to cope with the query ambiguity problem in search engines. In most existing studies, they have been investigated separately, but intuitively, they address the problem from two complementary perspectives and should be combined. Some recent work tried to combine them by restricting result diversification to the subtopics corresponding to the user's personal profile. However, diversification can be required even when the subtopics are outside the user's profile. In this paper, we propose a more general approach to integrate them based on users' implicit feedback in query logs. The proposed approach PER+DIV aggregates a document's novelty score and personal relevance score dynamically according to how much the query falls into the user's interests. To train the model based on user clicks in the logs, we consider user click as a result of both personal relevance and result diversity and a new method is proposed to isolate and model these two factors. To evaluate the model, we design several diversified and personalized metrics in addition to the traditional click-based metrics. Experimental results on a large-scale query log dataset show that the proposed integrated method significantly outperforms the existing personalization and diversification approaches.

Active learning is effective for tasks with limited labeled data by annotating a small set of data actively. It utilizes the current trained model to evaluate all unlabeled samples and annotates the best samples scored by a specific query strategy to update the underlying model iteratively. Most active learning approaches rely on only the current evaluation score but ignore the results from previous iterations. In this paper, we propose using more historical evaluation results which can provide additional information to help better select samples. First, we apply two heuristic features of the historical evaluation results, i.e. the weighted sum and the fluctuation of history sequences. Next, to make fuller use of the information contained in the historical results, we design a query strategy that learns to select samples based on the history sequence automatically. Our proposed idea is general and can be combined with both basic and state-of-the-art query strategies to achieve improvements. Experimental results show that our methods significantly promote existing methods.

Conversational search allows a user to interact with a search system in multiple turns. A query is strongly dependent on the conversation context. An effective way to improve retrieval effectiveness is to expand the current query with historical queries. However, not all the previous queries are related to, and useful for expanding the current query. In this paper, we propose a new method to select relevant historical queries that are useful for the current query. To cope with the lack of labeled training data, we use a pseudo-labeling approach to annotate useful historical queries based on their impact on the retrieval results. The pseudo-labeled data are used to train a selection model. We further propose a multi-task learning framework to jointly train the selector and the retriever during fine-tuning, allowing us to mitigate the possible inconsistency between the pseudo labels and the changed retriever. Extensive experiments on four conversational search datasets demonstrate the effectiveness and broad applicability of our method compared with several strong baselines.

This tutorial will provide an overview of recent advances on neuro-symbolic approaches for information retrieval. A decade ago, knowledge graphs and semantic annotations technology led to active research on how to best leverage symbolic knowledge. At the same time, neural methods have demonstrated to be versatile and highly effective.

As a means to understanding the healthiness of the food environment, obtaining big data (big food and other types) to model the built environment becomes critical. In this paper, we train and test seven different ML methods on bigdata from census data to predict the healthiness of the food environment. We introduce a synthetic ecosystem platform that can be used to bridge big data of different types combined with ML method for supporting food environment surveillance and intervention simulations. We illustrate with an example of neighborhood-level healthfulness assessment and conclude by a presentation of our next steps on employing machine learning to classify diet quality and recommend healthier food options to consumers.

The supply and demand of fresh food products must be tightly integrated to mitigate food waste, economic losses, and expansion of the environmental footprint. In this study, we use a novel loyalty program dataset from a grocery retailer in Quebec, Canada to predict demand for yogurt products for 17 months from 2015 to 2016. Focusing our attention on 13 newly launched yogurt products from a local manufacturer, we build and test 18 different machine learning models capable of predicting demand for individual products at the aggregate market level, as well as for each store. Store-level data were matched to neighborhood demographic data from the 2016 Canadian census to enrich features. Overall, 330 features were engineered to provide information on the product, marketing and promotions, store, and neighborhood over time. Analyses were conducted using Python 3 in Google Collaboratory and open-source libraries. Results from the best market-level model (random forest) achieve an r-squared of 84.0% on test data, while the store-level model (light gradient boosting machine) only achieves 57%. The results show that ML tools can be useful in modeling demand for new products at aggregate levels but achieving accurate predictions at more granular levels remains a hurdle to overcome. Insights for the preparation and analysis of loyalty data are discussed.

Contextual information in search sessions is important for capturing users' search intents. Various approaches have been proposed to model user behavior sequences to improve document ranking in a session. Typically, training samples of (search context, document) pairs are sampled randomly in each training epoch. In reality, the difficulty to understand user's search intent and to judge document's relevance varies greatly from one search context to another. Mixing up training samples of different difficulties may confuse the model's optimization process. In this work, we propose a curriculum learning framework for context-aware document ranking, in which the ranking model learns matching signals between the search context and the candidate document in an easy-to-hard manner. In so doing, we aim to guide the model gradually toward a global optimum. To leverage both positive and negative examples, two curricula are designed. Experiments on two real query log datasets show that our proposed framework can improve the performance of several existing methods significantly, demonstrating the effectiveness of curriculum learning for context-aware document ranking.

Multi-Task Learning (MTL) has attracted increasing attention in recommender systems. A crucial challenge in MTL is to learn suitable shared parameters among tasks and to avoid negative transfer of information. The most recent sparse sharing models use independent parameter masks, which only activate useful parameters for a task, to choose the useful subnet for each task. However, as all the subnets are optimized in parallel for each task independently, it is faced with the problem of conflict between parameter gradient updates (i.e, parameter conflict problem). To address this challenge, we propose a novel Contrastive Sharing Recommendation model in MTL learning (CSRec). Each task in CSRec learns from the subnet by the independent parameter mask as in sparse sharing models, but a contrastive mask is carefully designed to evaluate the contribution of the parameter to a specific task. The conflict parameter will be optimized relying more on the task which is more impacted by the parameter. Besides, we adopt an alternating training strategy in CSRec, making it possible to self-adaptively update the conflict parameters by fair competitions. We conduct extensive experiments on three real-world large scale datasets, i.e., Tencent Kandian, Ali-CCP and Census-income, showing better effectiveness of our model over state-of-the-art methods for both offline and online MTL recommendation scenarios.

Typical recommender systems try to mimic the past behaviors of users to make future recommendations. For example, in food recommendations, they tend to recommend the foods the user prefers. While the recommended foods may be easily accepted by the user, it cannot improve the user’s dietary habits for a specific goal such as weight control. In this paper, we build a food recommendation system that can be used on the web or in a mobile app to help users meet their goals on body weight, while also taking into account their health information (BMI) and the nutrition information of foods (calories). Instead of applying dietary guidelines as constraints, we build recommendation models from the successful behaviors of comparable users: the weight loss model is trained using the historical food consumption data of similar users who successfully lost weight. By combining such a goal-oriented recommendation model with a general model, the recommendations can be smoothly tuned toward the goal without disruptive food changes. We tested the approach on real data collected from a popular weight management app. It is shown that our recommendation approach can better predict the foods for test periods where the user truly meets the goal, than the typical existing approaches.

Active learning is an effective approach for tasks with limited labeled data. It samples a small set of data to annotate actively and is widely applied in various AI tasks. It uses an iterative process, during which we utilize the current trained model to evaluate all unlabeled samples and annotate the best samples based on a specific query strategy to update the underlying model iteratively. Most existing active learning approaches rely on only the evaluation results generated by the current model and ignore the results from previous iterations. In this paper, we propose using more historical evaluation results which can provide additional information to help better select samples. First, we apply two kinds of heuristic features of the historical evaluation results, the weighted sum of historical results and the fluctuation of the historical evaluation sequence, to improve the effectiveness of active learning sampling. Next, to further and more globally use the information contained in the historical results, we design a novel query strategy that learns how to select samples based on the historical sequences automatically. Our proposed idea is general and can be combined with both basic and state-of-the-art query strategies to achieve improvements. We test our approaches on two common NLP tasks including text classification and named entity recognition. Experimental results show that our methods significantly promote existing methods.

Due to the overload of published scientific articles, citation recommendation has long been a critical research problem for automatically recommending the most relevant citations of given articles. Relational topic models (RTMs) have shown promise on citation prediction via joint modeling of document contents and citations. However, existing RTMs can only capture pairwise or direct (first-order) citation relationships among documents. The indirect (high-order) citation links have been explored in graph neural network–based methods, but these methods suffer from the well-known explainability problem. In this article, we propose a model called Graph Neural Collaborative Topic Model that takes advantage of both relational topic models and graph neural networks to capture high-order citation relationships and to have higher explainability due to the latent topic semantic structure. Experiments on three real-world citation datasets show that our model outperforms several competitive baseline methods on citation recommendation. In addition, we show that our approach can learn better topics than the existing approaches. The recommendation results can be well explained by the underlying topics.

Generating a text based on a predefined guideline is an interesting but challenging problem. A series of studies have been carried out in recent years. In dialogue systems, researchers have explored driving a dialogue based on a plan, while in story generation, a storyline has also been proved to be useful. In this article, we address a new task—generating movie scripts based on a predefined narrative. As an early exploration, we study this problem in a “retrieval-based” setting. We propose a model (ScriptWriter-CPre) to select the best response (i.e., next script line) among the candidates that fit the context (i.e., previous script lines) as well as the given narrative. Our model can keep track of what in the narrative has been said and what is to be said. Besides, it can also predict which part of the narrative should be paid more attention to when selecting the next line of script. In our study, we find the narrative plays a different role than the context. Therefore, different mechanisms are designed for deal with them. Due to the unavailability of data for this new application, we construct a new large-scale data collection GraphMovie from a movie website where end-users can upload their narratives freely when watching a movie. This new dataset is made available publicly to facilitate other studies in text generation under the guideline. Experimental results on the dataset show that our proposed approach based on narratives significantly outperforms the baselines that simply use the narrative as a kind of context.

Context information in search sessions has proven to be useful for capturing user search intent. Existing studies explored user behavior sequences in sessions in different ways to enhance query suggestion or document ranking. However, a user behavior sequence has often been viewed as a definite and exact signal reflecting a user's behavior. In reality, it is highly variable: user's queries for the same intent can vary, and different documents can be clicked. To learn a more robust representation of the user behavior sequence, we propose a method based on contrastive learning, which takes into account the possible variations in user's behavior sequences. Specifically, we propose three data augmentation strategies to generate similar variants of user behavior sequences and contrast them with other sequences. In so doing, the model is forced to be more robust regarding the possible variations. The optimized sequence representation is incorporated into document ranking. Experiments on two real query log datasets show that our proposed model outperforms the state-of-the-art methods significantly, which demonstrates the effectiveness of our method for context-aware document ranking.

A proactive dialogue system has the ability to proactively lead the conversation. Different from the general chatbots which only react to the user, proactive dialogue systems can be used to achieve some goals, e.g., to recommend some items to the user. Background knowledge is essential to enable smooth and natural transitions in dialogue. In this paper, we propose a new multi-task learning framework for retrieval-based knowledge-grounded proactive dialogue. To determine the relevant knowledge to be used, we frame knowledge prediction as a complementary task and use explicit signals to supervise its learning. The final response is selected according to the predicted knowledge, the goal to achieve, and the context. Experimental results show that explicit modeling of knowledge prediction and goal selection can greatly improve the final response selection. Our code is available at https://github.com/DaoD/KPN/.

Graph Neural Networks (GNNs) such as GCN can effectively learn document representations via the semantic relation graph among documents and words. However, despite a few exceptions, most of the previous work in this line of research does not consider the underlying topical semantics inherited in document contents and the relation graph, making the representations less effective and hard to interpret. In a few recent studies trying to incorporate latent topics into GNNs, the topics have been learned independently from the relation graph modeling. Intuitively, topic extraction can benefit much from the information propagation of the relation graph structure - directly and indirectly connected documents and words have similar topics. In this paper, we propose a novel Graph Topic Neural Network (GTNN) model to mine latent topic semantics for interpretable document representation learning, taking into account the document-document, document-word, and word-word relationships in the graph. We also show that our model can be viewed as semi-amortized inference for relational topic model based on Poisson distribution, with high order correlations. We test our model in several settings: unsupervised, semi-supervised, and supervised representation learning, for both connected and unconnected documents. In all the cases, our model outperforms the state-of-the-art models for these tasks.

In social recommendation, the purchase decision of users is influenced by their basic preference of items, as well as the social influence of peers. Such social connections had been proved to be effective in modeling users' preference of items. However, most models in social recommender literature only considered two types of relations, i.e., user-item relation in interaction network and user-user relation in social network. The temporal sequential information of items, i.e., item-item relation, can also be utilized to infer the preference of users, but had been ignored in almost all of the graph based recommendation models. Two issues of such temporal information had not been well studied in social recommender systems: the temporal strength information, i.e., the real purchase time of an item, and its influence on social relations. To address the above issues, we propose a novel Temporal Enhanced Graph Model for Social Recommendation (TGRec). In TGRec, the purchase time information between items is characterized as a special temporal relation, and the purchase decision of users depends on three factors: (1) a user's basic preference of items, (2) the collaborative influence of peers, (3) the temporal impact of previous items bought by the user. Experimental results on three real-world commerce datasets demonstrate the effectiveness of our model for social recommendation, showing the usefulness of modeling the temporal information in heterogeneous graph.

Distant supervision provides a means to create a large number of weakly labeled data at low cost for relation classification. However, the resulting labeled instances are very noisy, containing data with wrong labels. Many approaches have been proposed to select a subset of reliable instances for neural model training, but they still suffer from noisy labeling problem or underutilization of the weakly-labeled data. To better select more reliable training instances, we introduce a small amount of manually labeled data as reference to guide the selection process. In this paper, we propose a meta-learning based approach, which learns to reweight noisy training data under the guidance of reference data. As the clean reference data is usually very small, we propose to augment it by dynamically distilling the most reliable elite instances from the noisy data. Experiments on several datasets demonstrate that the reference data can effectively guide the selection of training data, and our augmented approach consistently improves the performance of relation classification comparing to the existing state-of-the-art methods.

Electronic Health Record (EHR) coding is the task of assigning one or more International Classification of Diseases (ICD) codes to every EHR. Most previous work either ignores the hierarchical nature of the ICD codes or only focuses on parent-child relations. Moreover, existing EHR coding methods predict ICD codes from the leaf level with the greatest ICD number and the most fine-grained categories, which makes it difficult for models to make correct decisions. In order to address these problems, we model EHR coding as a path generation task. For this approach, we need to address two main challenges: (1) How to model relations between EHR and ICD codes, and relations between ICD codes? (2) How to evaluate the quality of generated ICD paths in order to obtain a signal that can be used to supervise the learning? We propose a coarse-to-fine ICD path generation framework, named Reinforcement Path Generation Network (RPGNet), that implements EHR coding with a Path Generator (PG) and a Path Discriminator (PD). We address challenge (1) by introducing a Path Message Passing (PMP) module in the PG to encode three types of relation: between EHRs and ICD codes, between parent-child ICD codes, and between sibling ICD codes. To address challgenge (2), we propose a PD component that estimates the reward for each ICD code in a generated path. RPGNet is trained with Reinforcement Learning (RL) in an adversarial manner. Experiments on the MIMIC-III benchmark dataset show that RPGNet significantly outperforms state-of-the-art methods in terms of micro-averaged F1 and micro-averaged AUC.

Applying reinforcement learning (RL) in recommender systems is attractive but costly due to the constraint of the interaction with real customers, where performing online policy learning through interacting with real customers usually harms customer experiences. A practical alternative is to build a recommender agent offline from logged data, whereas directly using logged data offline leads to the problem of selection bias between logging policy and the recommendation policy. The existing direct offline learning algorithms, such as Monte Carlo methods and temporal difference methods are either computationally expensive or unstable on convergence. To address these issues, we propose Pseudo Dyna-Q (PDQ). In PDQ, instead of interacting with real customers, we resort to a customer simulator, referred to as the World Model, which is designed to simulate the environment and handle the selection bias of logged data. During policy improvement, the World Model is constantly updated and optimized adaptively, according to the current recommendation policy. This way, the proposed PDQ not only avoids the instability of convergence and high computation cost of existing approaches but also provides unlimited interactions without involving real customers. Moreover, a proved upper bound of empirical error of reward function guarantees that the learned offline policy has lower bias and variance. Extensive experiments demonstrated the advantages of PDQ on two real-world datasets against state-of-the-arts methods.

Heterogeneous information network (HIN) contains multiple types of entities and relations. Most of existing HIN embedding methods learn the semantic information based on the heterogeneous structures between different entities, which are implicitly assumed to be complete. However, in real world, it is common that some relations are partially observed due to privacy or other reasons, resulting in a sparse network, in which the structure may be incomplete, and the ”unseen” links may also be positive due to the missing relations in data collection. To address this problem, we propose a novel and principled approach: a Multi-View Adversarial Completion Model (MV-ACM). Each relation space is characterized in a single viewpoint, enabling us to use the topological structural information in each view. Based on the multi-view architecture, an adversarial learning process is utilized to learn the reciprocity (i.e., complementary information) between different relations: In the generator, MV-ACM generates the complementary views by computing the similarity of the semantic representation of the same node in different views; while in the discriminator, MV-ACM discriminates whether the view is complementary by the topological structural similarity. Then we update the node’s semantic representation by aggregating neighborhoods information from the syncretic views. We conduct systematical experiments1 on six real-world networks from varied domains: AMiner, PPI, YouTube, Twitter, Amazon and Alibaba. Empirical results show that MV-ACM significantly outperforms the state-of-the-art approaches for both link prediction and node classification tasks.

In e-commerce, users' demands are not only conditioned by their profile and preferences, but also by their recent purchases that may generate new demands, as well as periodical demands that depend on purchases made some time ago. We call them respectively short-term demands and long-term demands. In this paper, we propose a novel self-attentive Continuous-Time Recommendation model (CTRec) for capturing the evolving demands of users over time. For modeling such time-sensitive demands, a Demand-aware Hawkes Process (DHP) framework is designed in CTRec to learn from the discrete purchase records of users. More specifically, a convolutional neural network is utilized to capture the short-term demands; and a self-attention mechanism is employed to capture the periodical purchase cycles of long-term demands. All types of demands are fused in DHP to make final continuous-time recommendations. We conduct extensive experiments on four real-world commercial datasets to demonstrate that CTRec is effective for general sequential recommendation problems, including next-item and next-session/basket recommendations. We observe in particular that CTRec is capable of learning the purchase cycles of products and estimating the purchase time of a product given a user.

Personalized search aims to adapt document ranking to user's personal interests. Traditionally, this is done by extracting click and topical features from historical data in order to construct a user profile. In recent years, deep learning has been successfully used in personalized search due to its ability of automatic feature learning. However, the small amount of noisy personal data poses challenges to deep learning models to learn the personalized classification boundary between relevant and irrelevant results. In this paper, we propose PSGAN, a Generative Adversarial Network (GAN) framework for personalized search. By means of adversarial training, we enforce the model to pay more attention to training data that are difficult to distinguish. We use the discriminator to evaluate personalized relevance of documents and use the generator to learn the distribution of relevant documents. Two alternative ways to construct the generator in the framework are tested: based on the current query or based on a set of generated queries. Experiments on data from a commercial search engine show that our models can yield significant improvements over state-of-the-art models.

Keyphrase extraction from documents is useful to a variety of applications such as information retrieval and document summarization. This paper presents an end-to-end method called DivGraphPointer for extracting a set of diversified keyphrases from a document. DivGraphPointer combines the advantages of traditional graph-based ranking methods and recent neural network-based approaches. Specifically, given a document, a word graph is constructed from the document based on word proximity and is encoded with graph convolutional networks, which effectively capture document-level word salience by modeling long-range dependency between words in the document and aggregating multiple appearances of identical words into one node. Furthermore, we propose a diversified point network to generate a set of diverse keyphrases out of the word graph in the decoding process. Experimental results on five benchmark data sets show that our proposed method significantly outperforms the existing state-of-the-art approaches.

Presents corrections to author information from the paper, “Characterizing and predicting early reviewers for effective product marketing on e-commerce websites,” (Bai, T., et al), IEEE Trans. Knowl. Data Eng., vol. 30, no. 12, pp. 2271–2284, Dec. 2018.

Modern Information Retrieval (IR) systems have become more and more complex, involving a large number of parameters. For example, a system may choose from a set of possible retrieval models (BM25, language model, etc.), or various query expansion parameters, whose values greatly influence the overall retrieval effectiveness. Traditionally, these parameters are set at a system level based on training queries, and the same parameters are then used for different queries. We observe that it may not be easy to set all these parameters separately, since they can be dependent. In addition, a global setting for all queries may not best fit all individual queries with different characteristics. The parameters should be set according to these characteristics. In this article, we propose a novel approach to tackle this problem by dealing with the entire system configurations (i.e., a set of parameters representing an IR system behaviour) instead of selecting a single parameter at a time. The selection of the best configuration is cast as a problem of ranking different possible configurations given a query. We apply learning-to-rank approaches for this task. We exploit both the query features and the system configuration features in the learning-to-rank method so that the selection of configuration is query dependent. The experiments we conducted on four TREC ad hoc collections show that this approach can significantly outperform the traditional method to tune system configuration globally (i.e., grid search) and leads to higher effectiveness than the top performing systems of the TREC tracks. We also perform an ablation analysis on the impact of different features on the model learning capability and show that query expansion features are among the most important for adaptive systems.

Search results personalization has become an effective way to improve the quality of search engines. Previous studies extracted information such as past clicks, user topical interests, query click entropy and so on to tailor the original ranking. However, few studies have taken into account the sequential information underlying previous queries and sessions. Intuitively, the order of issued queries is important in inferring the real user interests. And more recent sessions should provide more reliable personal signals than older sessions. In addition, the previous search history and user behaviors should influence the personalization of the current query depending on their relatedness. To implement these intuitions, in this paper we employ a hierarchical recurrent neural network to exploit such sequential information and automatically generate user profile from historical data. We propose a query-aware attention model to generate a dynamic user profile based on the input query. Significant improvement is observed in the experiment with data from a commercial search engine when compared with several traditional personalization models. Our analysis reveals that the attention model is able to attribute higher weights to more related past sessions after fine training.

Context-aware Recommendations (CARS) have attracted a lot of attention recently because of the impact of contextual information on user behaviors. Recent state-of-the-art methods represent the relations between users/items and contexts as a tensor, with which it is difficult to distinguish the impacts of different contextual factors and to model complex, non-linear interactions between contexts and users/items. In this paper, we propose a novel neural model, named Attentive Interaction Network (AIN), to enhance CARS through adaptively capturing the interactions between contexts and users/items. Specifically, AIN contains an Interaction-Centric Module to capture the interaction effects of contexts on users/items; a User-Centric Module and an Item-Centric Module to model respectively how the interaction effects influence the user and item representations. The user and item representations under interaction effects are combined to predict the recommendation scores. We further employ effect-level attention mechanism to aggregate multiple interaction effects. Extensive experiments on two rating datasets and one ranking dataset show that the proposed AIN outperforms state-of-the-art CARS methods. In addition, we also find that AIN provides recommendations with better explanation ability with respect to contexts than the existing approaches.

Next basket recommendation is a new type of recommendation, which recommends a set of items, or a basket, to the user. Purchase in basket is a common behavior of consumers. Recently, deep neural networks have been applied to model sequential transactions of baskets in next basket recommendation. However, current methods do not track the user's evolving appetite for items explicitly, and they ignore important item attributes such as product category. In this paper, we propose a novel Attribute-aware Neural Attentive Model (ANAM) to address these problems. ANAM adopts an attention mechanism to explicitly model user's evolving appetite for items, and utilizes a hierarchical architecture to incorporate the attribute information. In specific, ANAM utilizes a recurrent neural network to model the user's sequential behavior over time, and relays the user's appetite toward items and their attributes to next basket through attention weights shared across baskets on the two different hierarchies. Experiment results on two public datasets (ıe Ta-Feng and JingDong) demonstrate the effectiveness of our ANAM model for next basket recommendation.

Recent neural models for IR have produced good retrieval effectiveness compared with traditional models. Yet all of them assume that a single matching function should be used for all queries. In practice, user's queries may be of various nature which might require different levels of matching, from low level word matching to high level conceptual matching. To cope with this problem, we propose a multi-level abstraction convolutional model (MACM) that generates and aggregates several levels of matching scores. Weak supervision is used to address the problem of large training data. Experimental results demonstrated the effectiveness of our proposed MACM model.

Online reviews have become an important source of information for users before making an informed purchase decision. Early reviews of a product tend to have a high impact on the subsequent product sales. In this paper, we take the initiative to study the behavior characteristics of early reviewers through their posted reviews on two real-world large e-commerce platforms, i.e., Amazon and Yelp. In specific, we divide product lifetime into three consecutive stages, namelyearly,majority, andlaggards. A user who has posted a review in the early stage is considered as an early reviewer. We quantitatively characterize early reviewers based on their rating behaviors, the helpfulness scores received from others and the correlation of their reviews with product popularity. We have found that (1) an early reviewer tends to assign a higher average rating score; and (2) an early reviewer tends to post more helpful reviews. Our analysis of product reviews also indicates that early reviewers’ ratings and their received helpfulness scores are likely to influence product popularity. By viewing the review posting process as a multiplayer competition game, we propose a novel margin-based embedding model for early reviewer prediction. Extensive experiments on two different e-commerce datasets have shown that our proposed approach outperforms a number of competitive baselines.

Search result diversification aims to retrieve diverse results to satisfy as many different information needs as possible. Supervised methods have been proposed recently to learn ranking functions and they have been shown to produce superior results to unsupervised methods. However, these methods use implicit approaches based on the principle of Maximal Marginal Relevance (MMR). In this paper, we propose a learning framework for explicit result diversification where subtopics are explicitly modeled. Based on the information contained in the sequence of selected documents, we use the attention mechanism to capture the subtopics to be focused on while selecting the next document, which naturally fits our task of document selection for diversification. As a preliminary attempt, we employ recurrent neural networks and max pooling to instantiate the framework. We use both distributed representations and traditional relevance features to model documents in the implementation. The framework is flexible to model query intent in either a flat list or a hierarchy. Experimental results show that the proposed method significantly outperforms all the existing search result diversification approaches.

Search result diversification aims to retrieve diverse results to satisfy as many different information needs as possible. Supervised methods have been proposed recently to learn ranking functions and they have been shown to produce superior results to unsupervised methods. However, these methods use implicit approaches based on the principle of Maximal Marginal Relevance (MMR). In this paper, we propose a learning framework for explicit result diversification where subtopics are explicitly modeled. Based on the information contained in the sequence of selected documents, we use attention mechanism to capture the subtopics to be focused on while selecting the next document, which naturally fits our task of document selection for diversification. The framework is implemented using recurrent neural networks and max-pooling which combine distributed representations and traditional relevance features. Our experiments show that the proposed method significantly outperforms all the existing methods.

Click-through information is considered as a valuable source of users’ implicit relevance feedback for commercial search engines. As existing studies have shown that the search result position in a search engine result page (SERP) has a very strong influence on users’ examination behavior, most existing click models are position based, assuming that users examine results from top to bottom in a linear fashion. Although these click models have been successful, most do not take temporal information into account. As many existing studies have shown, click dwell time and click sequence information are strongly correlated with users’ perceived relevance and search satisfaction. Incorporating temporal information may be important to improve performance of user click models for Web searches. In this article, we investigate the problem of properly incorporating temporal information into click models. We first carry out a laboratory eye-tracking study to analyze users’ examination behavior in different click sequences and find that the user common examination path among adjacent clicks is linear. Next, we analyze the user dwell time distribution in different search logs and find that we cannot simply use a click dwell time threshold (e.g., 30 seconds) to distinguish relevant/irrelevant results. Finally, we propose a novel time-aware click model (TACM), which captures the temporal information of user behavior. We compare the TACM to several existing click models using two real-world search engine logs. Experimental results show that the TACM outperforms other click models in terms of both predicting click behavior (perplexity) and estimating result relevance (NDCG).

To address the difficulty in clipping articles from various mobile applications (apps), we propose a novel framework called UniClip, which allows a user to snap a screen of an article to save the whole article in one place. The key task of the framework is search by screenshots , which has three challenges: (1) how to represent a screenshot; (2) how to formulate queries for effective article retrieval; and (3) how to identify the article from search results. We solve these by (1) segmenting a screenshot into structural units called blocks, (2) formulating effective search queries by considering the role of each block, and (3) aggregating the search result lists of multiple queries. To improve efficiency, we also extend our approach with learning-to-rank techniques so that we can find the desired article with only one query. Experimental results show that our approach achieves high retrieval performance ( F 1 = 0.868), which outperforms baselines based on keyword extraction and chunking methods. Learning-to-rank models improve our approach without learning by about 6%. A user study conducted to investigate the usability of UniClip reveals that ours is preferred by 21 out of 22 participants for its simplicity and effectiveness.

Information Retrieval (IR) systems heavily rely on a large number of parameters, such as the retrieval model or various query expansion parameters, whose values greatly influence the overall retrieval effectiveness. However, setting all these parameters individually can often be a tedious task, since they can all affect one another, while also vary for different queries. We propose to tackle this problem by dealing with entire system configurations (i.e. a set of parameters representing an IR system) instead of single parameters, and to apply state-of-the-art Learning to Rank techniques to select the most appropriate configuration for a given query. The experiments we conducted on two TREC AdHoc collections show that this approach is feasible and significantly outperforms the traditional way to configure a system, as well as the top performing systems of the TREC tracks. We also show an analysis on the impact of different features on the model's learning capability.

Relevance is a fundamental concept in information retrieval (IR) studies. It is however often observed that relevance as annotated by secondary assessors may not necessarily mean usefulness and satisfaction perceived by users. In this study, we confirm the difference by a laboratory study in which we collect relevance annotations by external assessors, usefulness and user satisfaction information by users, for a set of search tasks. We also find that a measure based on usefulness rather than relevance annotated has a better correlation with user satisfaction. However, we show that external assessors are capable of annotating usefulness when provided with more search context information. In addition, we also show that it is possible to generate automatically usefulness labels when some training data is available. Our findings explain why traditional system-centric evaluation metrics are not well aligned with user satisfaction and suggest that a usefulness-based evaluation method can be defined to better reflect the quality of search systems perceived by the users.

In this paper we address the difficulty of clipping articles from mobile apps. We propose a service called UniClip that allows a user to save the full content of an article by snapping a screenshot part of it. UniClip leverages a huge amount of indexed web data to mine the article by starting with a snapped screenshot. We propose approaches to solve three challenges: (1) how to represent a screenshot; (2) how to formulate effective queries for retrieving a full article; and (3) how to rank the best URL at the top from multiple search result lists. Experimental results indicate that our approach is effective in achieving as high an $$F_1$$ F 1 measure as 0.905, which outperforms the best of three baseline methods by 18 points.

Users may strive to formulate an adequate textual query for their information need. Search engines assist the users by presenting query suggestions. To preserve the original search intent, suggestions should be context-aware and account for the previous queries issued by the user. Achieving context awareness is challenging due to data sparsity. We present a novel hierarchical recurrent encoder-decoder architecture that makes possible to account for sequences of previous queries of arbitrary lengths. As a result, our suggestions are sensitive to the order of queries in the context while avoiding data sparsity. Additionally, our model can suggest for rare, or long-tail, queries. The produced suggestions are synthetic and are sampled one word at a time, using computationally cheap decoding techniques. This is in contrast to current synthetic suggestion models relying upon machine learning pipelines and hand-engineered feature sets. Results show that our model outperforms existing context-aware approaches in a next query prediction setting. In addition to query suggestion, our architecture is general enough to be used in a variety of other applications.

Click-through information is considered as a valuable source of users' implicit relevance feedback. As user behavior is usually influenced by a number of factors such as position, presentation style and site reputation, researchers have proposed a variety of assumptions (i.e.~click models) to generate a reasonable estimation of result relevance. The construction of click models usually follow some hypotheses. For example, most existing click models follow the sequential examination hypothesis in which users examine results from top to bottom in a linear fashion. While these click models have been successful, many recent studies showed that there is a large proportion of non-sequential browsing (both examination and click) behaviors in Web search, which the previous models fail to cope with. In this paper, we investigate the problem of properly incorporating non-sequential behavior into click models. We firstly carry out a laboratory eye-tracking study to analyze user's non-sequential examination behavior and then propose a novel click model named Partially Sequential Click Model (PSCM) that captures the practical behavior of users. We compare PSCM with a number of existing click models using two real-world search engine logs. Experimental results show that PSCM outperforms other click models in terms of both predicting click behavior (perplexity) and estimating result relevance (NDCG and user preference test). We also publicize the implementations of PSCM and related datasets for possible future comparison studies.

In this paper, we explore the idea of social role theory (SRT) and propose a novel regularized topic model which incorporates SRT into the generative process of social media content. We assume that a user can play multiple social roles, and each social role serves to fulfil different duties and is associated with a role-driven distribution over latent topics. In particular, we focus on social roles corresponding to the most common social activities on social networks. Our model is instantiated on microblogs, i.e., Twitter and community question-answering (cQA), i.e., Yahoo!Answers, where social roles on Twitter include “originators” and “propagators”, and roles on cQA are “askers” and “answerers”. Both explicit and implicit interactions between users are taken into account and modeled as regularization factors. To evaluate the performance of our proposed method, we have conducted extensive experiments on two Twitter datasets and two cQA datasets. Furthermore, we also consider multi-role modeling for scientific papers where an author's research expertise area is considered as a social role. A novel application of detecting users' research interests through topical keyword labeling based on the results of our multi-role model has been presented. The evaluation results have shown the feasibility and effectiveness of our model.

Compression algorithms are important for data-oriented tasks, especially in the era of “Big Data.” Modern processors equipped with powerful SIMD instruction sets provide us with an opportunity for achieving better compression performance. Previous research has shown that SIMD-based optimizations can multiply decoding speeds. Following these pioneering studies, we propose a general approach to accelerate compression algorithms. By instantiating the approach, we have developed several novel integer compression algorithms, called Group-Simple, Group-Scheme, Group-AFOR, and Group-PFD, and implemented their corresponding vectorized versions. We evaluate the proposed algorithms on two public TREC datasets, a Wikipedia dataset, and a Twitter dataset. With competitive compression ratios and encoding speeds, our SIMD-based algorithms outperform state-of-the-art nonvectorized algorithms with respect to decoding speeds.

User's examination of search results is a key concept involved in all the click models. However, most studies assumed that eye fixation means examination and no further study has been carried out to better understand user's examination behavior. In this study, we design an experimental search engine to collect both the user's feedback on their examinations and the eye-tracking/click-through data. To our surprise, a large proportion (45.8%) of the results fixated by users are not recognized as being "read". Looking into the tracking data, we found that before the user actually "reads" the result, there is often a "skimming" step in which the user quickly looks at the result without reading it. We thus propose a two-stage examination model which composes of a first "from skimming to reading" stage (Stage 1) and a second "from reading to clicking" stage (Stage 2). We found that the biases (e.g. position bias, domain bias, attractiveness bias) considered in many studies impact in different ways in Stage 1 and Stage 2, which suggests that users make judgments according to different signals in different stages. We also show that the two-stage examination behaviors can be predicted with mouse movement behavior, which can be collected at large scale. Relevance estimation with the two-stage examination model also outperforms that with a single-stage examination model. This study shows that the user's examination of search results is a complex cognitive process that needs to be investigated in greater depth and this may have a significant impact on Web search.

Search result diversification (SRD) aims to select diverse documents from the search results in order to cover as many search intents as possible. A prerequisite is that the search results contain diverse documents. For this purpose, we investigate a new approach to SRD by diversifying the query. Expansion terms are selected from ConceptNet so as to cover as diverse aspects as possible. The experimental results on several TREC data sets show that our method can outperform the existing state-of-the-art approaches that do not diversify the query.

Recently, increasing attention has been given to a possible reinterpretation of information retrieval issues in the more general probabilistic framework offered by Quantum Theory.

Click models are developed to interpret clicks by making assumptions on how users browse the search result page. Most existing click models implicitly assume that all users are homogeneous and act in the same way when browsing the search results. However, a number of researches have shown that users have diverse behavioral patterns, which is also observed in this paper by eye-tracking experiments and click-through log analysis. As a uniform click model for all users can hardly capture the diverse click behavior, in this paper we incorporate user preferences into both a variety of existing click models and a novel click model. The experimental results on a large-scale click-through data set show consistent and significant performance improvement of the click models with user preferences integrated.

A large number of studies have been devoted to modeling the contents and interactions between users on Twitter. In this paper, we propose a method inspired from Social Role Theory (SRT), which assumes that a user behaves differently with different roles in the generation process of Twitter content. We consider the two most distinctive social roles on Twitter: originator and propagator, who respectively posts original messages and retweets or forwards the messages from others. In addition, we also consider role-specific social interactions, especially implicit interactions between users who share some common interests. All the above elements are integrated into a novel regularized topic model. We evaluate the proposed method on real Twitter data. The results show that our method is more effective than the existing ones which do not distinguish social roles.

Traditional information retrieval (IR) models use bag-of-words as the basic representation and assume that some form of independence holds between terms. Representing term dependencies and defining a scoring function capable of integrating such additional evidence is theoretically and practically challenging. Recently, Quantum Theory (QT) has been proposed as a possible, more general framework for IR. However, only a limited number of investigations have been made and the potential of QT has not been fully explored and tested. We develop a new, generalized Language Modeling approach for IR by adopting the probabilistic framework of QT. In particular, quantum probability could account for both single and compound terms at once without having to extend the term space artificially as in previous studies. This naturally allows us to avoid the weight-normalization problem, which arises in the current practice by mixing scores from matching compound terms and from matching single terms. Our model is the first practical application of quantum probability to show significant improvements over a robust bag-of-words baseline and achieves better performance on a stronger non bag-of-words baseline.

Query suggestion is a useful tool to help users formulate better queries. Although this has been found highly useful globally, its effect on different queries may vary. In this paper, we examine the impact of query suggestion on queries of different degrees of difficulty. It turns out that query suggestion is much more useful for difficult queries than easy queries. In addition, the suggestions for difficult queries should rely less on their similarity to the original query. In this paper, we use a learning-to-rank approach to select query suggestions, based on several types of features including a query performance prediction. As query suggestion has different impacts on different queries, we propose an adaptive suggestion approach that makes suggestions only for difficult queries. We carry out experiments on real data from a search engine. Our results clearly indicate that an approach targeting difficult queries can bring higher gain than a uniform suggestion approach.

Social annotations provide additional document description contributed by online users and they have been explored for improving search performance. However, most existing methods need offline analysis of the whole tagged corpus, which is computationally expensive and cannot fit specific queries well. In this paper, we propose to use tags for document re-ranking. Specifically, we first estimate document similarity by combining words and tags and then adjust the document ranks with the assumption that similar documents should have similar retrieval scores. On similarity estimation, we present a new feature extraction method, called CRMF, from which document similarity can be derived. The CRMF can integrate the content and relation properties of multiple views and mine their correspondence. Besides, it does not require that all the documents to have tags. We tested the proposed approach on collections which are derived from Clue Web and contain Delicious tags. The experimental results demonstrate the effectiveness of tags on document re-ranking, where CRMF is significantly better than other state-of-the-art methods using tags.

User generated social annotations provide extra information for describing document contents. In this paper, we propose an effective method to model the categorization property of social annotations and explore the potential of combining it with classical language models for improving retrieval performance. Specifically, a novel TR-LDA model is presented to take annotations as an additional source for generating document contents apart from the document itself. We provide strategies for representing and weighting the categorization property and develop an efficient inference algorithm, where space saving is taken into account. Experiments are carried out on synthetic datasets, where documents and queries come from the standard evaluation conference TREC and annotations come from the website Delicious.com. Our results demonstrate the effectiveness of the proposed method on the ad-hoc retrieval task, which significantly outperforms state-of-art baselines.

Web search is challenging partly due to the fact that search queries and Web documents use different language styles and vocabularies. This paper provides a quantitative analysis of the language discrepancy issue, and explores the use of clickthrough data to bridge documents and queries. We assume that a query is parallel to the titles of documents clicked on for that query. Two translation models are trained and integrated into retrieval models: A word-based translation model that learns the translation probability between single words, and a phrase-based translation model that learns the translation probability between multi-term phrases. Experiments are carried out on a real world data set. The results show that the retrieval systems that use the translation models outperform significantly the systems that do not. The paper also demonstrates that standard statistical machine translation techniques such as word alignment, bilingual phrase extraction, and phrase-based decoding, can be adapted for building a better Web document retrieval system.

Pseudo relevance feedback method is an effective method for query model refinement. Most existing pseudo relevance feedback methods only take into consideration the term distribution of the feedback documents, but omit the term's context information. This paper presents a graph-based method to improve query models, in which a word graph is constructed to encode terms and their co-occurrence dependencies within the feedback documents. Using a random walk, the weight of each term in the graph can be determined in a context-dependent manner, i.e. the weight of a term is strongly dependent on the weights of the connected context terms. Our experimental results on four TREC collections show that our proposed approach is more effective than the existing state-of-the-art approaches.

In this paper, we propose a model to integrate term dependencies. Different from previous studies, each pair of terms is assigned a different weight of dependency according to their utility to IR. The experiments show that our model can significantly outperform the previous dependency models using fixed weights.

Query suggestion aims to suggest relevant queries for a given query, which helps users better specify their information needs. Previous work on query suggestion has been limited to the same language. In this article, we extend it to cross-lingual query suggestion (CLQS): for a query in one language, we suggest similar or relevant queries in other languages. This is very important to the scenarios of cross-language information retrieval (CLIR) and other related cross-lingual applications. Instead of relying on existing query translation technologies for CLQS, we present an effective means to map the input query of one language to queries of the other language in the query log. Important monolingual and cross-lingual information such as word translation relations and word co-occurrence statistics, and so on, are used to estimate the cross-lingual query similarity with a discriminative model. Benchmarks show that the resulting CLQS system significantly outperforms a baseline system that uses dictionary-based query translation. Besides, we evaluate CLQS with French-English and Chinese-English CLIR tasks on TREC-6 and NTCIR-4 collections, respectively. The CLIR experiments using typical retrieval models demonstrate that the CLQS-based approach has significantly higher effectiveness than several traditional query translation methods. We find that when combined with pseudo-relevance feedback, the effectiveness of CLIR using CLQS is enhanced for different pairs of languages.

Smoothing document model with word graph is a new and effective method in information retrieval. Word graph can naturally incorporate the dependency between the words; random walk algorithm based on the graph can be used to estimate the weight of each vertex. In this paper, we present a new way to construct a local word graph for smoothing document model, which exploits the document's k nearest neighbors: the vertices represent the words in the document and its k nearest neighbors, and the weights of the edges are estimated through word co-occurrence in the local document set. We argue that word graph is a key factor to the performance in graph-based smoothing method. By using the local document set, we can obtain a document specific word graph, and achieve better retrieval performance. Experimental results on three TREC collections show that our proposed approach is effective.

Different queries require different ranking methods. It is however challenging to determine what queries are similar, and how to rank documents for them. In this paper, we propose a new method to cluster queries according to the similarity determined based on URLs in their answers. We then train specific ranking models for each query cluster. In addition, a cluster-specific measure of authority is defined to favor documents from authoritative websites on the corresponding topics. The proposed approach is tested using data from a search engine. It turns out that our proposed topic-dependent models can significantly improve the search results of eight most popular categories of queries.

As a good complement to page content, anchor texts have been extensively used, and proven to be useful, in commercial search engines. However, anchor texts have been assumed to be independent, whether they come from the same Web site or not. Intuitively, an anchor text from unrelated Web sites should be considered as stronger evidence than that from the same site. This paper proposes two new methods to take into account the possible relationships between anchor texts. We consider two relationships in this paper: links from the same site and links from related sites. The importance assigned to the anchor texts in these two situations is discounted. Experimental results show that these two new models outperform the baseline model which assumes independence between hyperlinks.

Incorporating features extracted from clickthrough data (called clickthrough features) has been demonstrated to significantly improve the performance of ranking models for Web search applications. Such benefits, however, are severely limited by the data sparseness problem, i.e., many queries and documents have no or very few clicks. The ranker thus cannot rely strongly on clickthrough features for document ranking. This paper presents two smoothing methods to expand clickthrough data: query clustering via Random Walk on click graphs and a discounting method inspired by the Good-Turing estimator. Both methods are evaluated on real-world data in three Web search domains. Experimental results show that the ranking models trained on smoothed clickthrough features consistently outperform those trained on unsmoothed features. This study demonstrates both the importance and the benefits of dealing with the sparseness problem in clickthrough data.

In this paper, we propose a new phrase-based IR model, which integrates a measure of "inseparability" of phrases. Our experiments show its high potential to produce large improvements in retrieval effectiveness.

Traditional information retrieval (IR) approaches assume that the indexing terms are independent, which is not true in reality. Although some previous studies have tried to consider term relationships, strong simplifications had to be made at the very basic indexing step, namely, dependent terms are assigned independent counts or probabilities.

Pseudo-relevance feedback assumes that most frequent terms in the pseudo-feedback documents are useful for the retrieval. In this study, we re-examine this assumption and show that it does not hold in reality - many expansion terms identified in traditional approaches are indeed unrelated to the query and harmful to the retrieval. We also show that good expansion terms cannot be distinguished from bad ones merely on their distributions in the feedback documents and in the whole collection. We then propose to integrate a term classification process to predict the usefulness of expansion terms. Multiple additional features can be integrated in this process. Our experiments on three TREC collections show that retrieval effectiveness can be much improved when term classification is used. In addition, we also demonstrate that good terms should be identified directly according to their possible impact on the retrieval effectiveness, i.e. using supervised learning, instead of unsupervised learning.

Dictionary-based approaches to query translation have been widely used in Cross-Language Information Retrieval (CLIR) experiments. However, translation has been not only limited by the coverage of the dictionary, but also affected by translation ambiguities. In this paper we propose a novel method of query translation that combines other types of term relation to complement the dictionary-based translation. This allows extending the literal query translation to related words, which produce a beneficial effect of query expansion in CLIR. In this paper, we model query translation by Markov Chains (MC), where query translation is viewed as a process of expanding query terms to their semantically similar terms in a different language. In MC, terms and their relationships are modeled as a directed graph, and query translation is performed as a random walk in the graph, which propagates probabilities to related terms. This framework allows us to incorporating different types of term relation, either between two languages or within the source or target languages. In addition, the iterative training process of MC allows us to attribute higher probabilities to the target terms more related to the original query, thus offers a solution to the translation ambiguity problem. We evaluated our method on three CLIR benchmark collections, and obtained significant improvements over traditional dictionary-based approaches.

User query is an element that specifies an information need, but it is not the only one. Studies in literature have found many contextual factors that strongly influence the interpretation of a query. Recent studies have tried to consider the user's interests by creating a user profile. However, a single profile for a user may not be sufficient for a variety of queries of the user. In this study, we propose to use query-specific contexts instead of user-centric ones, including context around query and context within query. The former specifies the environment of a query such as the domain of interest, while the latter refers to context words within the query, which is particularly useful for the selection of relevant term relations. In this paper, both types of context are integrated in an IR model based on language modeling. Our experiments on several TREC collections show that each of the context factors brings significant improvements in retrieval effectiveness.

Query suggestion aims to suggest relevant queries for a given query, which help users better specify their information needs. Previously, the suggested terms are mostly in the same language of the input query. In this paper, we extend it to cross-lingual query suggestion (CLQS): for a query in one language, we suggest similar or relevant queries in other languages. This is very important to scenarios of cross-language information retrieval (CLIR) and cross-lingual keyword bidding for search engine advertisement. Instead of relying on existing query translation technologies for CLQS, we present an effective means to map the input query of one language to queries of the other language in the query log. Important monolingual and cross-lingual information such as word translation relations and word co-occurrence statistics, etc. are used to estimate the cross-lingual query similarity with a discriminative model. Benchmarks show that the resulting CLQS system significantly out performs a baseline system based on dictionary-based query translation. Besides, the resulting CLQS is tested with French to English CLIR tasks on TREC collections. The results demonstrate higher effectiveness than the traditional query translation methods.

Document and query expansions have been used separately in previous studies to enhance the representation of documents and queries. In this paper, we propose a general method that integrates both of them. Expansion is carried out using multi-stage Markov chains. Our experiments show that this method significantly outperforms the existing approaches.

No abstract available.

Noisy parallel corpora have been widely used for Cross-language information retrieval (CLIR). However, the previous studies only focus on truly parallel corpus. In this paper, we examine two possible approaches to exploit noisy corpora: filtering out noise from the corpora or adapting the training process of translation model to the noise corpora. Our experiments show that the second approach is better suited to CLIR.

This paper presents a study of three statistical query translation models that use different units of translation. We begin with a review of a word-based translation model that uses co-occurrence statistics for resolving translation ambiguities. The translation selection problem is then formulated under the framework of graphic model resorting to which the modeling assumptions and limitations of the co-occurrence model are discussed, and the research of finding better translation units is motivated. Then, two other models that use larger, linguistically motivated translation units (i.e., noun phrase and dependency triple) are presented. For each model, the modeling and training methods are described in detail. All query translation models are evaluated using TREC collections. Results show that larger translation units lead to more specific models that usually achieve better translation and cross-language information retrieval results.

Language Modeling (LM) has been successfully applied to Information Retrieval (IR). However, most of the existing LM approaches only rely on term occurrences in documents, queries and document collections. In traditional unigram based models, terms (or words) are usually considered to be independent. In some recent studies, dependence models have been proposed to incorporate term relationships into LM, so that links can be created between words in the same sentence, and term relationships (e.g. synonymy) can be used to expand the document model. In this study, we further extend this family of dependence models in the following two ways: (1) Term relationships are used to expand query model instead of document model, so that query expansion process can be naturally implemented; (2) We exploit more sophisticated inferential relationships extracted with Information Flow (IF). Information flow relationships are not simply pairwise term relationships as those used in previous studies, but are between a set of terms and another term. They allow for context-dependent query expansion. Our experiments conducted on TREC collections show that we can obtain large and significant improvements with our approach. This study shows that LM is an appropriate framework to implement effective query expansion.

Latent Semantic Indexing (LSI) has been successfully applied to information retrieval and text classification. However, when LSI is used in classification, some important features for small classes may be ignored because of their small feature values. To solve this problem, we propose the latent semantic classification (LSC) model which extends the LSI model in the following way: the classification information of the training documents is introduced into the latent semantic structure via a second set of latent variables, so that both indexing and classification information can be taken into account during the classification process. Our experiments on Reuters show that our new model performs better than the existing classification methods such as kNN and SVM.

In this paper, we propose a novel dependency language modeling approach for information retrieval. The approach extends the existing language modeling approach by relaxing the independence assumption. Our goal is to build a language model in which various word relationships can be integrated. In this work, we integrate two types of relationship extracted from WordNet and co-occurrence relationships respectively. The integrated model has been tested on several TREC collections. The results show that our model achieves substantial and significant improvements with respect to the models without these relationships. These results clearly show the benefit of integrating word relationships into language models for IR.

This paper presents a new discriminative model for information retrieval (IR), referred to as linear discriminant model (LDM), which provides a flexible framework to incorporate arbitrary features. LDM is different from most existing models in that it takes into account a variety of linguistic features that are derived from the component models of HMM that is widely used in language modeling approaches to IR. Therefore, LDM is a means of melding discriminative and generative models for IR. We present two algorithms of parameter learning for LDM. One is to optimize the average precision (AP) directly using an iterative procedure. The other is a perceptron-based algorithm that minimizes the number of discordant document-pairs in a rank list. The effectiveness of our approach has been evaluated on the task of ad hoc retrieval using six English and Chinese TREC test sets. Results show that (1) in most test sets, LDM significantly outperforms the state-of-the-art language modeling approaches and the classical probabilistic retrieval model; (2) it is more appropriate to train LDM using a measure of AP rather than likelihood if the IR system is graded on AP; and (3) linguistic features (e.g. phrases and dependences) are effective for IR if they are incorporated properly.

Text classification usually assumed a word-based document representation. In this paper, we propose a new approach to integrate compound terms in Bayesian text classification. Compound terms are used as complementary features to single words. An acute problem is to consider their dependence with the component words. In this paper, we propose to use smoothing techniques to combine both compound term and word representations. Experiments have been conducted on two corpora. Our results show that this approach can slightly but steadily improve the classification performance on both test corpora.

This paper presents a new dependence language modeling approach to information retrieval. The approach extends the basic language modeling approach based on unigram by relaxing the independence assumption. We integrate the linkage of a query as a hidden variable, which expresses the term dependencies within the query as an acyclic, planar, undirected graph. We then assume that a query is generated from a document in two stages: the linkage is generated first, and then each term is generated in turn depending on other related terms according to the linkage. We also present a smoothing method for model parameter estimation and an approach to learning the linkage of a sentence in an unsupervised manner. The new approach is compared to the classical probabilistic retrieval model and the previously proposed language models with and without taking into account term dependencies. Results show that our model achieves substantial and significant improvements on TREC collections.

Abstract A number of studies have examined the problems of query expansion in monolingual Information Retrieval (IR), and query translation for crosslanguage IR. However, no link has been made between them. This article first shows that query translation is a special case of query expansion. There is also another set of studies on inferential IR. Again, there is no relationship established with query translation or query expansion. The second claim of this article is that logical inference is a general form that covers query expansion and query translation. This analysis provides a unified view of different subareas of IR. We further develop the inferential IR approach in two particular contexts: using fuzzy logic and probability theory. The evaluation formulas obtained are shown to strongly correspond to those used in other IR models. This indicates that inference is indeed the core of advanced IR.

Queries to search engines on the Web are usually short. They do not provide sufficient information for an effective selection of relevant documents. Previous research has proposed the utilization of query expansion to deal with this problem. However, expansion terms are usually determined on term co-occurrences within documents. In this study, we propose a new method for query expansion based on user interactions recorded in user logs. The central idea is to extract correlations between query terms and document terms by analyzing user logs. These correlations are then used to select high-quality expansion terms for new queries. Compared to previous query expansion methods, ours takes advantage of the user judgments implied in user logs. The experimental results show that the log-based query expansion method can produce much better results than both the classical search method and the other query expansion methods.

Bilingual dictionaries have been commonly used for query translation in cross-language information retrieval (CLIR). However, we are faced with the problem of translation selection. Several recent studies suggested the utilization of term co-occurrences in this selection. This paper presents two extensions to improve them. First, we extend the basic co-occurrence model by adding a decaying factor that decreases the mutual information when the distance between the terms increases. Second, we incorporate a triple translation model, in which syntactic dependence relations (represented as triples) are integrated. Our evaluation on translation accuracy shows that translating triples as units is more precise than a word-by-word translation. Our CLIR experiments show that the addition of the decaying factor leads to substantial improvements of the basic co-occurrence model; and the triple translation model brings further improvements.

Query expansion has long been suggested as an effective way to resolve the short query and word mismatching problems. A number of query expansion methods have been proposed in traditional information retrieval. However, these previous methods do not take into account the specific characteristics of web searching; in particular, of the availability of large amount of user interaction information recorded in the web query logs. In this study, we propose a new method for query expansion based on query logs. The central idea is to extract probabilistic correlations between query terms and document terms by analyzing query logs. These correlations are then used to select high-quality expansion terms for new queries. The experimental results show that our log-based probabilistic query expansion method can greatly improve the search performance and has several advantages over other existing methods.

Query clustering is a process used to discover frequently asked questions or most popular topics on a search engine. This process is crucial for search engines based on question-answering. Because of the short lengths of queries, approaches based on keywords are not suitable for query clustering. This paper describes a new query clustering method that makes use of user logs which allow us to identify the documents the users have selected for a query. The similarity between two queries may be deduced from the common documents the users selected for them. Our experiments show that a combination of both keywords and user logs is better than using either method alone.

Dictionaries have often been used for query translation in cross-language information retrieval (CLIR). However, we are faced with the problem of translation ambiguity, i.e. multiple translations are stored in a dictionary for a word. In addition, a word-by-word query translation is not precise enough. In this paper, we explore several methods to improve the previous dictionary-based query translation. First, as many as possible, noun phrases are recognized and translated as a whole by using statistical models and phrase translation patterns. Second, the best word translations are selected based on the cohesion of the translation words. Our experimental results on TREC English-Chinese CLIR collection show that these techniques result in significant improvements over the simple dictionary approaches, and achieve even better performance than a high-quality machine translation system.

Query clustering is crucial for automatically discovering frequently asked queries (FAQs) or most popular topics on a question-answering search engine. Due to the short length of queries, the traditional approaches based on keywords are not suitable for query clustering. This paper describes our attempt to cluster similar queries according to their contents as well as the document click information in the user logs.

In order to increase retrieval precision, some new search engines provide manually verified answers to Frequently Asked Queries (FAQs). An underlying task is the identification of FAQs. This paper describes our attempt to cluster similar queries according to their contents as well as user logs. Our preliminary results show that the resulting clusters provide useful information for FAQ identification.

This paper describes the use of a probabilistic translation model to cross-language IR (CLIR). The performance of this approach is compared with that using machine translation (MT). It is shown that using a probabilistic model, we are able to obtain performances close to those using an MT system. In addition, we also investigated the possibility of automatically gather parallel texts from the Web in an attempt to construct a reasonable training corpus. The result is very encouraging. We showed that in several tests, such a training corpus is as good as a manually constructed one for CLIR purposes.

In previous studies, Chinese text retrieval has often been dealt with on the character basis.This approach is not suited to deal with complex queries.We suggest that Chirmse text retrieval should work with words inslead of characters.The crucial problem is to segment originally continuous Chinese texts into words.In this paper, wc Ilrsi propose a hybrid segmentation approach which unifies the commonly used approaches.The systcm SMART is then udaptcd to index the segmented Chinese texls.Finally, wc suggest that Chinese text retrieval should move further to include a thesaurus in order to cope with dle rich vocabulary of Chinese.

Users of a given information retrieval system may have different requirements at various times (sometimes emphasizing precision, sometimes recall), and the corpus may have different degree of emphasis regarding subjects.Therefore, a general purpose system should have parameters to allow adjustable performance.This article investigates the integration of several evaluation methods into a single system so that a user may choose an appropriate method or a combination of methods for his query evaluation.

Semantic-based approaches to Information Retrieval make a query evaluation similar to an inference process based on semantic relations. Semantic-based approaches find out hidden semantic relationships between a document and a query, but quantitative estimation of the correspondence between them is often empiric. On the other hand, probabilistic approaches usually consider only statistical relationships between terms. It is expected that improvement may be brought by integrating these two approaches. This paper demonstrates, using some particular probabilistic models which are strongly related to modal logic, that such an integration is feasible and natural. A new model is developed on the basis of an extended modal logic. It has the advantages of : (1) augmenting a semantic-based approach with a probabilistic measurement, and (2) augmenting a probabilistic approach with finer semantic relations than just statistical ones. It is shown that this model verifies most of the conditions for an absolute probability function.

This paper focuses on the query processing module of RIME, an experimental prototype of an intelligent information retrieval system designed to manage high-precision queries on a corpus of medical reports. Though highly specific this particular corpus is representative of an important class of applications: information retrieval among full-text specialized documents which constitute critical sources of information in several organizations (medicine, law, space industry…). This experience allowed us to design and implement an elaborate model for the semantic content of the documents which is an extension of the Conceptual Dependency approach. The underlying retrieval model is inspired from the Logic model proposed by C.J. Van Rijsbergen, which has been considerably refined using an Extended Modal Logic. After presenting the context of the RIME project, we briefly describe the models designed for the internal representation of medical reports and queries. The main part of the paper is then devoted to the retrieval model and its application to the query processing module of RIME which has a natural language interface. Processing a query involves two main phases: the interpretation which transforms the natural language query into a search expression, and the evaluation phases which retrieves the corresponding medical reports. We focus here on the evaluation phases and show its relationship with the underlying retrieval model. Evaluations from practical experiments are also given, along with indications about current developments of the project.

This paper is a contribution to the construction of a general model for information retrieval. As in the paper of Van Rijsbergen ([RIJ86]), the implicit base in all information retrieval systems is considered as a logical implication. The measure of correspondence between a document and a query is transformed into the estimation of the strength (or certainty) of logical implication. The modal logics will show its suitability for representing the behavior of information retrieval systems. In existing Information Retrieval models, several aspects are often mixed. A part of this paper is contributed to separate these aspects to give a clearer view of information retrieval systems. This general model is also compared with some existing models to show its generality.