Bundle recommender system is divided into two main stages: bundle editing and bundle recommendation. While substantial research progress has been made in each stage, in practical application scenarios, bundle compositions and the final recommended bundles mutually influence each other: the continuously editing bundle compositions affect the recommendation results, while user feedback on recommended bundles in turn guides the refinement of bundle compositions. This paper presents the first comprehensive reproducibility study of the complete bundle recommendation pipeline. We implement eight bundle-level editing methods, nine item-level editing methods, and seven state-of-the-art bundle recommendation models, and evaluate their performance across six real-world datasets. Our empirical analysis reveals several key findings. First, bundle-level editing faces the challenge of generating high-quality bundles. Second, in the item-level editing, the replacement operation emerges as a universal bottleneck across all methods. Third, in the recommendation stage, recommendation models exhibit varying performance across different interaction density scenarios (e.g., cold-start). Finally, bundle recommendation suffers degraded performance when integrating item-level editing and bundle recommendation within a unified pipeline. Overall, there is the systemic limitation of bundle recommendation: prior work has focused on optimizing individual stages independently, disregarding the interdependencies throughout the entire recommendation system. These findings highlight the urgent need to develop end-to-end solutions that can holistically address the bundle editing and recommendation workflow. Our repository is now available for public access via https://github.com/anyr123/Bundle_Edit_Rec_SIGIR26.

Generative inference with Large Language Models (LLMs) is the cornerstone of web-scale AI search, where queries are answered using vast, heterogeneous documents retrieved via Retrieval-Augmented Generation (RAG). This paradigm is critically bottlenecked by the cost of self-attention mechanism on long context. The sheer diversity of retrieved web content (multi-sourced, multi-lingual, multi-faceted) makes simple Key-Value (KV) cache optimizations with pre-fixed subsets ineffective, demanding a dynamic, content-aware approach. This challenge, however, introduces a classic chicken-and-egg problem: the model cannot foresee the necessary KV entries for attention without first inferring on the content, yet doing so on the full context is prohibitively expensive. This paper introduces P&F, a unified framework that resolves this dilemma through a core ''probe-and-fetch'' mechanism, which ingeniously integrates with speculative decoding -- an acceleration approach already adopted in web-scale AI search. The probe step repurposes the speculative draft model: while generating candidate tokens, it simultaneously probes the context to predict the most salient KV entries the large model will need for attention. The fetch step immediately acts on this prediction, asynchronously fetching these sparse entries from memory. This synergistic design piggybacks the probing step onto the drafting process, allowing the expensive gathering of a sparse KV cache to be fully masked. Crucially, this co-design breaks the sequential dependency bottleneck that cripples naive integrations of speculative decoding and prefetching due to synchronization issues. Extensive experiments show P&F significantly outperforms state-of-the-art methods in throughput and scalability, offering a practical, drop-in solution. Extensive offline evaluations across various settings and datasets demonstrate that P&F yields superior throughput and scalability compared to advanced baselines, while maintaining model quality across diverse models and scales. In online settings, P&F delivers substantial gains in throughput improvements while preserving response quality, making it well-suited for large-scale industrial deployment in real-time AI Search services.

Cold-start bundle recommendation focuses on modeling new bundles with insufficient information to provide recommendations. Advanced bundle recommendation models usually learn bundle representations from multiple views (e.g., user-bundle interaction views) at both bundle and item levels. Consequently, the cold-start problem for bundles is more challenging than that for traditional items due to the dual-level multi-view complexity. For cold-start bundle recommendation, we propose a novel Mixture of Diffusion Experts (MoDiffE) framework, which employs a divide-and-conquer strategy and consists of three parts: (1) Division : The bundle cold-start problem is divided into view-specific but unified sub-problems: the poor representation of feature-missing bundles in prior-embedding models. (2) Conquest : Diffusion models uniformly solve all sub-problems by directly generating diffusion representations without depending on specific features. (3) Combination : A cold-aware hierarchical Mixture of Experts (MoE) is employed to adaptively combine results of the sub-problems into final recommendations. Additionally, MoDiffE proposes a cold-start gating augmentation method to enable gating for cold bundles. In experiments on three real-world datasets, MoDiffE significantly outperforms existing solutions in cold-start bundle recommendation. It achieves up to a 0.1027 Recall@20 improvement in cold-start scenarios and up to a 47.43% relative improvement in all-bundle scenarios.

Knowledge graph reasoning (KGR) is a key technology that infers missing facts in knowledge graphs (KGs). Given that real-world scenarios typically encounter unseen KGs with new entities and new relations, researchers have begun to explore fully inductive KGR methods. This setting presents greater challenges and has not been fully explored. Current methods primarily construct relation graphs based on the original KG to facilitate message passing between relations. These models have made significant progress in achieving fully inductive reasoning. However, as relation graphs focus solely on the co-occurrence patterns between relations, they often fail to capture reasoning patterns in KGs, which causes the model to struggle in effectively distinguishing between different relations and entities. This limitation severely restrict the reasoning capabilities of existing methods. In light of this, we propose the Adaptive Rule Pattern Transfer model (AdaRPT) for KGR. It aims to leverage logical rules for each relation in the KG to learn more comprehensive and transferable knowledge representations for entities and relations. For entities, we design a non-parameter message passing model that aggregates path information from the query entity to other entities. The path information for each entity is then matched with rules to obtain the transferable feature of each entity. And for relations, we extract both reasoning and co-occurrence patterns from KGs as transferable relation features. Finally, a path-based graph neural network (GNN) is employed on the transferable features of entities and relations to perform reasoning on KGs. Extensive experimental evaluations on 43 datasets for both inductive and transductive reasoning demonstrate the effectiveness and generalization capability of AdaRPT.

In the field of information Retrieval (IR), Pseudo-relevance feedback (PRF) and Query Expansion (QE) techniques have garnered significant attention for their efficacy in enhancing retrieval effectiveness. However, traditional PRF approaches predominantly concentrate solely on pseudo-relevant documents identified during the initial retrieval stage, neglecting the rich semantic information embedded within non-pseudo-relevant documents. This paper introduces an innovative PRF model that integrates soft negative samples and contrastive learning to address this limitation, aiming for a more comprehensive capture and representation of semantics. First, we employ the BM25 algorithm as the baseline retrieval mechanism to accurately pinpoint pseudo-relevant documents from the first stage retrieval and assign weights to their terms. Second, a contrastive learning strategy is introduced to distill semantic features from all documents globally, further refining the semantic weights of terms. To mitigate the risk of information loss associated with soft negative samples, we ingeniously leverage the statistical properties of kernel function to precisely gauge the co-occurrence frequencies between terms, ensuring the preservation of core information and thus obtaining kernel function term co-occurrence weights. Third, we select semantically related terms highly relevant to the query for creating an optimized query by balancing these three weight distributions. Extensive empirical analyses conducted on several TREC datasets demonstrate the practical feasibility of our proposed model. It outperforms baseline models and state-of-the-art technologies on core evaluation metrics such as MAP, P@10, NDCG, and MRR. Deeper comparative experiments and case studies reveal that the expansion terms generated by our model exhibits a deeper level of semantic coherence with the original query, underscoring the dual advantages of the model in both theory and practice. In summary, the model presented herein not only opens a new path at the technical level, but also provides a more accurate and efficient solution for real-world applications in IR.

Conversational retrieval leverages multi-turn conversations to meet users’ information needs, and accurately understanding the new intent has become a significant challenge in this field. Recently, the language comprehension and reasoning capabilities of large language models (LLMs) offer a viable solution to these challenges. In this article, we propose a new Dual-Query Generation and Joint-Encoding method by utilizing LLM for Conversational Information Seeking, abbreviated as DQ-CIS. Specifically, we propose a dual-query generation approach that leverages both open source and closed source LLMs to generate two complementary queries: a full-rewrite query that preserves the context semantics of the conversation and a condensed-rewrite query that emphasizes the core intent of the current query. Additionally, to better express the semantic information of the query, we propose a dual-query joint-encoding method, which enhances the thematic expression of query vectors by treating the dual-query as semantic complementary. A query coverage fine-tuned semantic matching method is also introduced to improve result relevance and ranking by fine-tuning the original retrieval scores by ColBERT. We conducted a number of experiments on seven publicly available conversational retrieval datasets. The results show that compared with other models, DQ-CIS has strong competitiveness in both retrieval efficiency and retrieval results.

Meal recommendation, as a typical health-related recommendation task, contains complex relationships between users, courses, and meals. Among them, meal-course affiliation associates user-meal and user-course interactions. However, an extensive literature review demonstrates that there is a lack of publicly available meal recommendation datasets including meal-course affiliation. Meal recommendation research has been constrained in exploring the impact of cooperation between two levels of interaction on personalization and healthiness. To pave the way for meal recommendation research, we introduce a new benchmark dataset called MealRec^+. Due to constraints related to user health privacy and meal scenario characteristics, the collection of data that includes both meal-course affiliation and two levels of interactions is impeded. Therefore, a simulation method is adopted to derive meal-course affiliation and user-meal interaction from the user's dining sessions simulated based on user-course interaction data. Then, two well-known nutritional standards are used to calculate the healthiness scores of meals. Moreover, we experiment with several baseline models, including separate and cooperative interaction learning methods. Our experiment demonstrates that cooperating the two levels of interaction in appropriate ways is beneficial for meal recommendations. The dataset is available on GitHub (https://github.com/WUT-IDEA/MealRecPlus).

As the field of machine reading comprehension (MRC) continues to evolve, it is unlocking enormous potential for its practical application. However, the currently well-performing models predominantly rely on massive pre-trained language models with at least several hundred million or even over one hundred billion parameters. These complex models not only require immense computational power but also extensive storage, presenting challenges for resource-limited environments such as online education.Current research indicates that specific capabilities of larger models can be transferred to smaller models through knowledge distillation. However, prior to our work, there were no small models specifically designed for MRC task with complex reasoning abilities. In light of this, we present a novel multi-teacher multi-stage distillation approach, MTMS. It facilitates the easier deployment of reasoning-based MRC task on resource-constrained devices, thereby enabling effective applications. In this method, we design a multi-teacher distillation framework that includes both a logical teacher and a semantic teacher. This framework allows MTMS to simultaneously extract features from different perspectives of the text, mitigating the limitations inherent in single-teacher information representations. Furthermore, we introduce a multi-stage contrastive learning strategy. Through this strategy, the student model can progressively align with the teacher models, effectively bridging the gap between them. Extensive experimental outcomes on two inference-based datasets from real-world scenarios demonstrate that MTMS requires nearly 10 times fewer parameters compared with the teacher model size while achieving the competitive performance.

The task of machine reading comprehension (MRC) is to enable machine to read and understand a piece of text and then answer the corresponding question correctly. This task requires machine to not only be able to perform semantic understanding but also possess logical reasoning capabilities. Just like human reading, it involves thinking about the text from two interacting perspectives of semantics and logic. However, previous methods based on reading comprehension either consider only the logical structure of the text or only the semantic structure of the text and cannot simultaneously balance semantic understanding and logical reasoning. This single form of reasoning cannot make the machine fully understand the meaning of the text. Additionally, the issue of sparsity in composition presents a significant challenge for models that rely on graph-based reasoning. To this end, a cross-graph knowledge propagation network (CGKPN) with adaptive connection is presented to address the above issues. The model first performs self-view node embedding on the constructed logical graph and semantic graph to update the representations of the graphs. Specifically, a relevance matrix between nodes is introduced to adaptively adjust node connections in response to the challenge posed by sparse graph. Subsequently, CGKPN conducts cross-graph knowledge propagation on nodes that are identical in both graphs, effectively resolving conflicts arising from identical nodes in different views, and enabling the model to better integrate the logical and semantic relationships of the text through efficient interaction. Experiments on the two MRC datasets ReClor and LogiQA indicate the superior performance of our proposed model CGKPN compared to other existing baselines.

Knowledge Graph Completion (KGC) has garnered massive research interest recently, and most existing methods are designed following a transductive setting where all entities are observed during training. Despite the great progress on the transductive KGC, these methods struggle to conduct reasoning on emerging KGs involving unseen entities. Thus, inductive KGC, which aims to deduce missing links among unseen entities, has become a new trend. Many existing studies transform inductive KGC as a graph classification problem by extracting enclosing subgraphs surrounding each candidate triple. Unfortunately, they still face certain challenges, such as the expensive time consumption caused by the repeat extraction of enclosing subgraphs, and the deficiency of entity-independent feature learning. To address these issues, we propose a global-local anchor representation (GLAR) learning method for inductive KGC. Unlike previous methods that utilize enclosing subgraphs, we extract a shared opening subgraph for all candidates and perform reasoning on it, enabling the model to perform reasoning more efficiently. Moreover, we design some transferable global and local anchors to learn rich entity-independent features for emerging entities. Finally, a global-local graph reasoning model is applied on the opening subgraph to rank all candidates. Extensive experiments show that our GLAR outperforms most existing state-of-the-art methods.

Dialogue systems for non-English languages have long been under-explored. In this paper, we take the first step to investigate few-shot cross-lingual transfer learning (FS-XLT) and multitask learning (MTL) in the context of open-domain dialogue generation for non-English languages with limited data. We observed catastrophic forgetting in both FS-XLT and MTL for all 6 languages in our preliminary experiments. To mitigate the issue, we propose a simple yet effective prompt learning approach that can preserve the multilinguality of multilingual pre-trained language model (mPLM) in FS-XLT and MTL by bridging the gap between pre-training and fine-tuning with Fixed-prompt LM Tuning and our hand-crafted prompts. Experimental results on all 6 languages in terms of both automatic and human evaluations demonstrate the effectiveness of our approach. Our code is available at https://github.com/JeremyLeiLiu/XLinguDial.

Online shopping platforms, such as Amazon and AliExpress, are increasingly prevalent in society, helping customers purchase products conveniently. With recent progress in natural language processing, researchers and practitioners shift their focus from traditional product search to conversational product search. Conversational product search enables user-machine conversations and through them collects explicit user feedback that allows to actively clarify the users’ product preferences. Therefore, prospective research on an intelligent shopping assistant via conversations is indispensable. Existing publications on conversational product search either model conversations independently from users, queries, and products or lead to a vocabulary mismatch. In this work, we propose a new conversational product search model, ConvPS, to assist users in locating desirable items. The model is first trained to jointly learn the semantic representations of user, query, item, and conversation via a unified generative framework. After learning these representations, they are integrated to retrieve the target items in the latent semantic space. Meanwhile, we propose a set of greedy and explore-exploit strategies to learn to ask the user a sequence of high-performance questions for conversations. Our proposed ConvPS model can naturally integrate the representation learning of the user, query, item, and conversation into a unified generative framework, which provides a promising avenue for constructing accurate and robust conversational product search systems that are flexible and adaptive. Experimental results demonstrate that our ConvPS model significantly outperforms state-of-the-art baselines.

Collaborative Filtering (CF) has emerged as fundamental paradigms for parameterizing users and items into latent representation space, with their correlative patterns from interaction data. Among various CF techniques, the development of GNN-based recommender systems, e.g., PinSage and LightGCN, has offered the state-of-the-art performance. However, two key challenges have not been well explored in existing solutions: i) The over-smoothing effect with deeper graph-based CF architecture, may cause the indistinguishable user representations and degradation of recommendation results. ii) The supervision signals (i.e., user-item interactions) are usually scarce and skewed distributed in reality, which limits the representation power of CF paradigms. To tackle these challenges, we propose a new self-supervised recommendation framework Hypergraph Contrastive Collaborative Filtering (HCCF) to jointly capture local and global collaborative relations with a hypergraph-enhanced cross-view contrastive learning architecture. In particular, the designed hypergraph structure learning enhances the discrimination ability of GNN-based CF paradigm, in comprehensively capturing the complex high-order dependencies among users. Additionally, our HCCF model effectively integrates the hypergraph structure encoding with self-supervised learning to reinforce the representation quality of recommender systems, based on the hypergraph self-discrimination. Extensive experiments on three benchmark datasets demonstrate the superiority of our model over various state-of-the-art recommendation methods, and the robustness against sparse user interaction data. The implementation codes are available at https://github.com/akaxlh/HCCF.

Cross-lingual entity alignment has attracted considerable attention in recent years. Past studies using conventional approaches to match entities share the common problem of missing important structural information beyond entities in the modeling process. This allows graph neural network models to step in. Most existing graph neural network approaches model individual knowledge graphs (KGs) separately with a small amount of pre-aligned entities served as anchors to connect different KG embedding spaces. However, this characteristic can cause several major problems, including performance restraint due to the insufficiency of available seed alignments and ignorance of pre-aligned links that are useful in contextual information in-between nodes. In this article, we propose DuGa-DIT, a dual gated graph attention network with dynamic iterative training, to address these problems in a unified model. The DuGa-DIT model captures neighborhood and cross-KG alignment features by using intra-KG attention and cross-KG attention layers. With the dynamic iterative process, we can dynamically update the cross-KG attention score matrices, which enables our model to capture more cross-KG information. We conduct extensive experiments on two benchmark datasets and a case study in cross-lingual personalized search. Our experimental results demonstrate that DuGa-DIT outperforms state-of-the-art methods.

In this article, we propose a Latent Dirichlet Allocation– (LDA) based topic-graph probabilistic personalization model for Web search. This model represents a user graph in a latent topic graph and simultaneously estimates the probabilities that the user is interested in the topics, as well as the probabilities that the user is not interested in the topics. For a given query issued by the user, the webpages that have higher relevancy to the interested topics are promoted, and the webpages more relevant to the non-interesting topics are penalized. In particular, we simulate a user’s search intent by building two profiles: A positive user profile for the probabilities of the user is interested in the topics and a corresponding negative user profile for the probabilities of being not interested in the the topics. The profiles are estimated based on the user’s search logs. A clicked webpage is assumed to include interesting topics. A skipped (viewed but not clicked) webpage is assumed to cover some non-interesting topics to the user. Such estimations are performed in the latent topic space generated by LDA. Moreover, a new approach is proposed to estimate the correlation between a given query and the user’s search history so as to determine how much personalization should be considered for the query. We compare our proposed models with several strong baselines including state-of-the-art personalization approaches. Experiments conducted on a large-scale real user search log collection illustrate the effectiveness of the proposed models.

Neural attention, an emerging technique used to identify important inputs within neural networks, have become increasingly popular in the area of recommender systems. Not only allowing to better identify what defines users and items, attention-based recommender systems are further able to provide accompanying explanations. However, these representations usually capture only part of users' preferences and items' attributes, resulting in limited reasoning and accuracy. We therefore propose Dual Attention Recommender with Items and Attributes (DARIA), a novel approach able to combine two dependable neural attention mechanisms to better justify its suggestions. Utilizing the personalized history of users, DARIA identifies the most relevant past activities while considering the real-world features that contributed to the similarity. In addition, we adopt the novel approach of self-attention and introduce Self-Attention Recommender based on Attributes and History (SARAH). As a variation to DARIA, SARAH utilizes two self-attention components to describe users by their most characteristic past activities and items by their best depicting attributes. Various experiments establish the significant improvement of SARAH and DARIA over seven key baselines in diverse recommendation settings. By comparing our two proposed frameworks, we demonstrate the potential benefit of applying self-attention in different scenarios.

For sequential recommendation, it is essential to capture and predict future or long-term user preference for generating accurate recommendation over time. To improve the predictive capacity, we adopt reinforcement learning (RL) for developing effective sequential recommenders. However, user-item interaction data is likely to be sparse, complicated and time-varying. It is not easy to directly apply RL techniques to improve the performance of sequential recommendation.

In this paper, we study collaborative filtering in an interactive setting, in which the recommender agents iterate between making recommendations and updating the user profile based on the interactive feedback. The most challenging problem in this scenario is how to suggest items when the user profile has not been well established, \ie recommend for cold-start users or warm-start users with taste drifting. Existing approaches either rely on overly pessimistic linear exploration strategy or adopt meta-learning based algorithms in a full exploitation way. In this work, to quickly catch up with the user's interests, we proposed to represent the exploration policy with a neural network and directly learn it from the feedback data. Specifically, the exploration policy is encoded in the weights of multi-channel stacked self-attention neural networks and trained with efficient Q-learning by maximizing users' overall satisfaction in the recommender systems. The key insight is that the satisfied recommendations triggered by the exploration recommendation can be viewed as the exploration bonus (delayed reward) for its contribution on improving the quality of the user profile. Therefore, the proposed exploration policy, to balance between learning the user profile and making accurate recommendations, can be directly optimized by maximizing users' long-term satisfaction with reinforcement learning. Extensive experiments and analysis conducted on three benchmark collaborative filtering datasets have demonstrated the advantage of our method over state-of-the-art methods.

Pseudo‐relevance feedback is a well‐studied query expansion technique in which it is assumed that the top‐ranked documents in an initial set of retrieval results are relevant and expansion terms are then extracted from those documents. When selecting expansion terms, most traditional models do not simultaneously consider term frequency and the co‐occurrence relationships between candidate terms and query terms. Intuitively, however, a term that has a higher co‐occurrence with a query term is more likely to be related to the query topic. In this article, we propose a kernel co‐occurrence‐based framework to enhance retrieval performance by integrating term co‐occurrence information into the Rocchio model and a relevance language model (RM3). Specifically, a kernel co‐occurrence‐based Rocchio method (KRoc) and a kernel co‐occurrence‐based RM3 method (KRM3) are proposed. In our framework, co‐occurrence information is incorporated into both the factor of the term discrimination power and the factor of the within‐document term weight to boost retrieval performance. The results of a series of experiments show that our proposed methods significantly outperform the corresponding strong baselines over all data sets in terms of the mean average precision and over most data sets in terms of P@10. A direct comparison of standard Text Retrieval Conference data sets indicates that our proposed methods are at least comparable to state‐of‐the‐art approaches.

Understanding user preference is of key importance for an effective recommender system. For comprehensive user profiling, many efforts have been devoted to extract user feature-level preference from the review information. Despite effectiveness, existing methods mostly assume linear relationships among the users, items, and features, and the collaborative information is usually utilized in an implicit and insufficient manner, which limits the recommender capacity in modeling users’ diverse preferences. For bridging this gap, in this article, we propose to formulate user feature-level preferences by a neural signed hypergraph and carefully design the information propagation paths for diffusing collaborative filtering signals in a more effective manner. By taking the advantages of the neural model’s powerful expressiveness, the complex relationship patterns among users, items, and features are sufficiently discovered and well utilized. By infusing graph structure information into the embedding process, the collaborative information is harnessed in a more explicit and effective way. We conduct comprehensive experiments on real-world datasets to demonstrate the superiorities of our model.

Open source softwares play an important role in information retrieval research. Most of the existing open source information retrieval systems are implemented in Java or C++ programming language. In this paper, we propose Parrot1, a Python-based interactive platform for information retrieval research. The proposed platform has mainly three advantages in comparison with the existing retrieval systems: (1) It is integrated with Jupyter Notebook, an interactive programming platform which has proved to be effective for data scientists to tackle big data and AI problems. As a result, users can interactively visualize and diagnose a retrieval model; (2) As an application written in Python, it can be easily used in combination with the popular deep learning frameworks such as Tersorflow and Pytorch; (3) It is designed especially for researchers. Less code is needed to create a new retrieval model or to modify an existing one. Our efforts have focused on three functionalists: good usability, interactive programming, and good interoperability with the popular deep learning frameworks. To confirm the performance of the proposed system, we conduct comparative experiments on a number of standard test collections. The experimental results show that the proposed system is both efficient and effective, providing a practical framework for researchers in information retrieval.

We propose OurDirection, an open-domain dialogue framework that is specialized in mimicking the Hansard (debate) materials from Canadian House of Commons. In this framework, we employed two sets of neural network models (Hierarchical Recurrent Encoder-Decoder (HRED) and RNN) to generate the dialogue responses. Extensive experiments on Hansard dataset shows that the models can learn the structure of the debates, and can produce reasonable responses to the user entries.

The neural networks have attracted great attention for sentence similarity modeling in recent years. Most neural networks focus on the representation of each sentence, while the common features of a sentence pair are not well studied. In this paper, we propose a Collaborative and Adversarial Network (CAN), which explicitly models the common features between two sentences for enhancing sentence similarity modeling. To be specific, a common feature extractor is presented and embedded into our CAN model, which includes a generator and a discriminator playing a collaborative and adversarial game for common feature extraction. Experiments on three benchmark datasets, namely TREC-QA and WikiQA for answer selection and MSRP for paraphrase identification, show that our proposed model is effective to boost the performance of sentence similarity modeling. In particular, our proposed model outperforms the state-of-the-art approaches on TREC-QA without using any external resources or pre-training. For the other two datasets, our model is also comparable to if not better than the recent neural network approaches.

In probabilistic BM25, term frequency normalization is one of the key components. It is often controlled by parameters $k_1$ and b , which need to be optimized for each given data set. In this paper, we assume and show empirically that term frequency normalization should be specific with query length in order to optimize retrieval performance. Following this intuition, we first propose a new term frequency normalization with query length for probabilistic information retrieval, namely \textttBM25\tiny QL . Then \textttBM25\tiny QL is incorporated into the state-of-the-art models CRTER riptsize 2 and LDA-BM25, denoted as $\textttCRTER riptsize 2 ^\texttt\tiny QL $ and \textttLDA-BM25\tiny QL respectively. A series of experiments show that our proposed approaches \textttBM25\tiny QL , $\textttCRTER riptsize 2 ^\texttt\tiny QL $ and \textttLDA-BM25\tiny QL are comparable to BM25, CRTER riptsize 2 and LDA-BM25 with the optimal b setting in terms of MAP on all the data sets.

One of the main challenges in medical image retrieval is the increasing volume of image data, which render it difficult for domain experts to find relevant information from large data sets. Effective and efficient medical image retrieval systems are required to better manage medical image information. Text‐based image retrieval (TBIR) was very successful in retrieving images with textual descriptions. Several TBIR approaches rely on models based on bag‐of‐words approaches, in which the image retrieval problem turns into one of standard text‐based information retrieval; where the meanings and values of specific medical entities in the text and metadata are ignored in the image representation and retrieval process. However, we believe that TBIR should extract specific medical entities and terms and then exploit these elements to achieve better image retrieval results. Therefore, we propose a novel reranking method based on medical‐image‐dependent features. These features are manually selected by a medical expert from imaging modalities and medical terminology. First, we represent queries and images using only medical‐image‐dependent features such as image modality and image scale. Second, we exploit the defined features in a new reranking method for medical image retrieval. Our motivation is the large influence of image modality in medical image retrieval and its impact on image‐relevance scores. To evaluate our approach, we performed a series of experiments on the medical ImageCLEF data sets from 2009 to 2013. The BM25 model, a language model, and an image‐relevance feedback model are used as baselines to evaluate our approach. The experimental results show that compared to the BM25 model, the proposed model significantly enhances image retrieval performance. We also compared our approach with other state‐of‐the‐art approaches and show that our approach performs comparably to those of the top three runs in the official ImageCLEF competition.

Query expansion under the pseudo-relevance feedback (PRF) framework has been extensively studied in information retrieval. However, most expansion methods are mainly based on the statistics of single terms, which can generate plenty of irrelevant query terms and decrease retrieval performance. To alleviate this problem, we propose an approach that adapts the PRF-based contextual snippets into a context-aware topic model to enhance query representations. Specifically, instead of selecting a series of independent terms, we make full use of the query contextual information and focus on the snippets with the length ofnin the PRF documents. Furthermore, we propose a context-aware topic (CAT) model to mine the topic distributions of the query-relevant snippets, namely, fine contextual snippets. In contrast to the traditional topic models that infer the topics from the whole corpus, we establish a bridge between the snippets and the corresponding PRF documents, which can be used for modeling the topics more precisely and efficiently. Finally, the topic distributions of the fine snippets are used for context-aware and topic-sensitive query representations. To evaluate the performance of our approach, we integrate the obtained queries into a topic-based hybrid retrieval model and conduct extensive experiments on various TREC collections. The experimental results show that our query-modeling approach is more effective in boosting retrieval performance compared with the state-of-the-art methods.

Temporal information has been widely used to promote the information retrieval (IR) performance, especially for microblog search which usually prefers the latest news and events. Previous studies mainly focused on incorporating the document-level temporal information into retrieval, while the temporal relevance of each query word was not well investigated. In this paper, we propose a word temporal predictor to characterize the word-level temporal relevance by fine-grained time-aware kernel density estimation over the feedback documents. In addition, we present a fine-grained time-aware framework to integrate the proposed word temporal predictor with the traditional document temporal predictor for retrieval. Finally, we incorporate the framework into two state-of-the-art retrieval models, namely language model (LM) and BM25. The experimental results on the TREC 2011-2014 Microblog collections, show that our proposed word temporal predictor is effective to boost the retrieval performance within both LM and BM25 frameworks. In particular, we achieve significant improvements over the strong baselines with optimized settings in most cases. Furthermore, our fine-grained time-aware models with word temporal predictor are comparable to if not better than the state-of-the-art temporal retrieval models.

A variable annuity is a tax-deferred retirement vehicle created to address concerns that many people have about outliving their assets. In the past decade, the rapid growth of variable annuities has posed great challenges to insurance companies especially when it comes to valuing the complex guarantees embedded in these products.

Attention based recurrent neural networks (RNN) have shown a great success for question answering (QA) in recent years. Although significant improvements have been achieved over the non-attentive models, the position information is not well studied within the attention-based framework. Motivated by the effectiveness of using the word positional context to enhance information retrieval, we assume that if a word in the question (i.e., question word) occurs in an answer sentence, the neighboring words should be given more attention since they intuitively contain more valuable information for question answering than those far away. Based on this assumption, we propose a positional attention based RNN model, which incorporates the positional context of the question words into the answers' attentive representations. Experiments on two benchmark datasets show the great advantages of our proposed model. Specifically, we achieve a maximum improvement of 8.83% over the classical attention based RNN model in terms of mean average precision. Furthermore, our model is comparable to if not better than the state-of-the-art approaches for question answering.

For diversity and novelty evaluation in information retrieval, we expect that the novel documents are always ranked higher than the redundant ones and the relevant ones higher than the irrelevant ones. We also expect that the level of novelty and relevancy should be acknowledged. Accordingly, we expect that the evaluation algorithm would reward rankings that respect these expectations. Nevertheless, there are few research articles in the literature that study how to meet such expectations, even fewer in the field of biomedical information retrieval. In this article, we propose a new metric for novelty and relevancy evaluation in biomedical information retrieval based on an aspect‐level performance measure introduced by TREC Genomics Track with formal results to show that those expectations above can be respected under ideal conditions. The empirical evaluation indicates that the proposed metric,geNov, is greatly sensitive to the desired characteristics above, and the three parameters are highly tuneable for different evaluation preferences. By experimentally comparing with state‐of‐the‐art metrics for novelty and diversity, the proposed metric shows its advantages in recognizing the ranking quality in terms of novelty, redundancy, relevancy, and irrelevancy and in its discriminative power. Experiments reveal the proposed metric is faster to compute than state‐of‐the‐art metrics.

The abundance of medical resources has encouraged the development of systems that allow for efficient searches of information in large medical image data sets. State‐of‐the‐art image retrieval models are classified into three categories: content‐based (visual) models, textual models, and combined models. Content‐based models use visual features to answer image queries, textual image retrieval models use word matching to answer textual queries, and combined image retrieval models, use both textual and visual features to answer queries. Nevertheless, most of previous works in this field have used the same image retrieval model independently of the query type. In this article, we define a list of generic and specific medical query features and exploit them in an association rule mining technique to discover correlations between query features and image retrieval models. Based on these rules, we propose to use an associative classifier (NaiveClass) to find the best suitable retrieval model given a new textual query. We also propose a second associative classifier (SmartClass) to select the most appropriate default class for the query. Experiments are performed on Medical ImageCLEF queries from 2008 to 2012 to evaluate the impact of the proposed query features on the classification performance. The results show that combining our proposed specific and generic query features is effective in query classification.

Community question answering (cQA) has become an important issue due to the popularity of cQA archives on the Web. This paper focuses on addressing the lexical gap problem in question retrieval. Question retrieval in cQA archives aims to find the existing questions that are semantically equivalent or relevant to the queried questions. However, the lexical gap problem brings a new challenge for question retrieval in cQA. In this paper, we propose to model and learn distributed word representations with metadata of category information within cQA pages for question retrieval using two novel category powered models. One is a basic category powered model called MB-NET and the other one is an enhanced category powered model called ME-NET which can better learn the distributed word representations and alleviate the lexical gap problem. To deal with the variable size of word representation vectors, we employ the framework of fisher kernel to transform them into the fixed-length vectors. Experimental results on large-scale English and Chinese cQA data sets show that our proposed approaches can significantly outperform state-of-the-art retrieval models for question retrieval in cQA. Moreover, we further conduct our approaches on large-scale automatic evaluation experiments. The evaluation results show that promising and significant performance improvements can be achieved.

Sentiment classification aims to automatically predict sentiment polarity (e.g., positive or negative) of user generated sentiment data (e.g., reviews, blogs). In real applications, these user-generated sentiment data can span so many different domains that it is difficult to label the training data for all of them. Therefore, we study the problem of sentiment classification adaptation task in this article. That is, a system is trained to label reviews from one source domain but is meant to be used on the target domain. One of the biggest challenges for sentiment classification adaptation task is how to deal with the problem when two data distributions between the source domain and target domain are significantly different from one another. However, our observation is that there might exist some domain shared knowledge among certain input dimensions of different domains. In this article, we present a novel method for modeling and mining the domain shared knowledge from different sentiment review domains via a joint non-negative matrix factorization–based framework. In this proposed framework, we attempt to learn the domain shared knowledge and the domain-specific information from different sentiment review domains with several various regularization constraints. The advantage of the proposed method can promote the correspondence under the topic space between the source domain and the target domain, which can significantly reduce the data distribution gap across two domains. We conduct extensive experiments on two real-world balanced data sets from Amazon product reviews for sentence-level and document-level binary sentiment classification. Experimental results show that our proposed approach significantly outperforms several strong baselines and achieves an accuracy that is competitive with the most well-known methods for sentiment classification adaptation.

Traditional information retrieval (IR) models, in which a document is normally represented as a bag of words and their frequencies, capture the term-level and document-level information. Topic models, on the other hand, discover semantic topic-based information among words. In this paper, we consider term-based information and semantic information as two features of query terms and propose a simple enhancement for ad-hoc IR via topic modeling. In particular, three topic-based hybrid models, LDA-BM25, LDA-MATF and LDA-LM, are proposed. A series of experiments on eight standard datasets show that our proposed models can always outperform significantly the corresponding strong baselines over all datasets in terms of MAP and most of datasets in terms of [email protected] and [email protected] A direct comparison on eight standard datasets also indicates our proposed models are at least comparable to the state-of-the-art approaches.

Using approximate inference techniques, we investigate in this paper the applicability of Bayesian Networks to the problem of ranking a large set of documents. Topology of the network is a bipartite. Network parameters (conditional probability distributions) are determined through an adoption of the weighting scheme tf-idf. Rank of a document with respect to a given query is defined as the corresponding posterior probability, which is estimated through performing Rejection Sampling. Experimental results suggest that performance of the model is at least comparable to the baseline ones such as BM25. The framework of this model potentially offers new and novel ways in weighting documents. Integrating the model with other ranking algorithms, meanwhile, is expected to bring in performance improvement in document ranking.

Most of the existing information retrieval models assume that the terms of a text document are independent of each other. These retrieval models integrate three major variables to determine the degree of importance of a term for a document: within document term frequency, document length and the specificity of the term in the collection. Intuitively, the importance of a term for a document is not only dependent on the three aspects mentioned above, but also dependent on the degree of semantic coherence between the term and the document. In this paper, we propose a heuristic approach, in which the degree of semantic coherence of the query terms with a document is adopted to improve the information retrieval performance. Experimental results on standard TREC collections show the proposed models consistently outperform the state-of-the-art models.

Pseudo relevance feedback (PRF) has shown to be effective in ad hoc information retrieval. In traditional PRF methods, top‐ranked documents are all assumed to be relevant and therefore treated equally in the feedback process. However, the performance gain brought by each document is different as showed in our preliminary experiments. Thus, it is more reasonable to predict the performance gain brought by each candidate feedback document in the process of PRF. We define the quality level (QL) and then use this information to adjust the weights of feedback terms in these documents. Unlike previous work, we do not make any explicit relevance assumption and we go beyond just selecting “good” documents for PRF. We propose a quality‐based PRF framework, in which two quality‐based assumptions are introduced. Particularly, two different strategies, relevance‐based QL (RelPRF) and improvement‐based QL (ImpPRF) are presented to estimate the QL of each feedback document. Based on this, we select a set of heterogeneous document‐level features and apply a learning approach to evaluate the QL of each feedback document. Extensive experiments on standard TREC (Text REtrieval Conference) test collections show that our proposed model performs robustly and outperforms strong baselines significantly.

Traditional pseudo relevance feedback (PRF) models choose top k feedback documents for query expansion and treat those documents equally. When k is determined, feedback terms are selected without considering the reliability of these documents for relevance. Because the performance of PRF is sensitive to the selection of feedback terms, noisy terms imported from these irrelevant documents or partially relevant documents will harm the final results extensively. Intuitively, terms in these documents should be considered less important for feedback term selection. Nonetheless, how to measure the reliability of feedback documents is a difficult problem. Recently, topic modeling has become more and more popular in the information retrieval (IR) area. In order to identify how reliable a feedback document is to be relevant, we attempt to adapt the topical information into PRF. However, topics are hard to be quantified and therefore the identification of topic is usually fuzzy. It is very challenging for integrating the obtained topical information effectively into IR and other text-processing-related areas. Current research work mainly focuses on mining relevant information from particular topics. This is extremely difficult when the boundaries of different topics are hard to define. In this article, we investigate a key factor of this problem, the topic number for topic modeling and how it makes topics “fuzzy.” To effectively and efficiently apply topical information, we propose a new probabilistic framework, “TopPRF,” and three models, TS-COS, TS-EU, and TS-Entropy, via integrating “Topic Space” (TS) information into pseudo relevance feedback. These methods discover how reliable a document is to be relevant through both term and topical information. When selecting feedback terms, candidate terms in more reliable feedback documents should obtain extra weights. Experimental results on various public collections justify that our proposed methods can significantly reduce the influence of “fuzzy topics” and obtain stable, good results over the strong baseline models. Our proposed probabilistic framework, TopPRF, and three topic-space-based models are capable of searching documents beyond traditional term matching only and provide a promising avenue for constructing better topic-space-based IR systems. Moreover, in-depth discussions and conclusions are made to help other researchers apply topical information effectively.

Nouns are more important than other parts of speech in information retrieval and are more often found near the beginning or the end of sentences. In this paper, we investigate the effects of rewarding terms based on their location in sentences on information retrieval. Particularly, we propose a novel Term Location (TEL) retrieval model based on BM25 to enhance probabilistic information retrieval, where a kernel-based method is used to capture term placement patterns. Experiments on five TREC datasets of varied size and content indicate the proposed model significantly outperforms the optimized BM25 and DirichletLM in MAP over all datasets with all kernel functions, and excels the optimized BM25 and DirichletLM over most of the datasets in [email protected] and [email protected] with different kernel functions.

Pseudo Relevance Feedback is an effective technique to improve the performance of ad-hoc information retrieval. Traditionally, the expansion terms are extracted either according to the term distributions in the feedback documents; or according to both the term distributions in the feedback documents and in the whole document collection. However, most of the existing models employ a single term frequency normalization mechanism or criteria that cannot take into account various aspects of a term's saliency in the feedback documents. In this paper, we propose a simple and heuristic, but effective model, in which three term frequency transformation techniques are integrated to capture the saliency of a candidate term associated with the original query terms in the feedback documents. Through evaluations and comparisons on six TREC collections, we show that our proposed model is effective and generally superior to the recent progress of relevance feedback models.

We propose to enhance proximity-based probabilistic retrieval models with more contextual information. A term pair with higher contextual relevance of term proximity is assigned a higher weight. Several measures are proposed to estimate the contextual relevance of term proximity. We assume the top ranked documents from a basic weighting model are more relevant to the query, and calculate the contextual relevance of term proximity using the top ranked documents. We propose a context-sensitive proximity model, and the experimental results on standard TREC data sets show the effectiveness of our proposed model.

Traditionally, in many probabilistic retrieval models, query terms are assumed to be independent. Although such models can achieve reasonably good performance, associations can exist among terms from a human being’s point of view. There are some recent studies that investigate how to model term associations/dependencies by proximity measures. However, the modeling of term associations theoretically under the probabilistic retrieval framework is still largely unexplored. In this article, we introduce a new concept cross term , to model term proximity, with the aim of boosting retrieval performance. With cross terms, the association of multiple query terms can be modeled in the same way as a simple unigram term. In particular, an occurrence of a query term is assumed to have an impact on its neighboring text. The degree of the query-term impact gradually weakens with increasing distance from the place of occurrence. We use shape functions to characterize such impacts. Based on this assumption, we first propose a bigram CRoss TErm Retrieval ( CRTER 2 ) model as the basis model, and then recursively propose a generalized n-gram CRoss TErm Retrieval ( CRTER n ) model for n query terms, where n > 2. Specifically, a bigram cross term occurs when the corresponding query terms appear close to each other, and its impact can be modeled by the intersection of the respective shape functions of the query terms. For an n-gram cross term, we develop several distance metrics with different properties and employ them in the proposed models for ranking. We also show how to extend the language model using the newly proposed cross terms. Extensive experiments on a number of TREC collections demonstrate the effectiveness of our proposed models.

The increasing quantities of available medical resources have motivated the development of effective search tools and medical decision support systems. Medical image search tools help physicians in searching medical image datasets for diagnosing a disease or monitoring the stage of a disease given previous patient's image screenings. Image retrieval models are classified into three categories: content-based (visual), textual and combined models. In most of previous work, a unique image retrieval model is applied for any user formulated query independently of what retrieval model best suits the information need behind the query. The main challenge in medical image retrieval is to cope the semantic gap between user information needs and retrieval models. In this paper, we propose a novel approach for finding correlations between medical query features and retrieval models based on association rule mining. We define new medical-dependent query features such as image modality and presence of specific medical image terminology and make use of existing generic query features such as query specificity, ambiguity and cohesiveness. The proposed query features are then exploited into association rule mining for discovering rules which correlate query features to visual, textual or combined image retrieval models. Based on the discovered rules, we propose to use an associative classifier that finds the best suitable rule with a maximum feature coverage for a new query. Experiments are performed on Image CLEF queries from 2008 to 2012 where we evaluate the impact of our proposed query features on the classification performance. Results show that combining our proposed specific and generic query features is effective for classifying queries. A comparative study between our classifier, CBA, Naïve Bayes, Bayes Net and decision trees showed that our best coverage associative classifier outperforms existing classifiers where it achieves an improvement of 30%.

In information retrieval, we are interested in the information that is not only relevant but also novel. In this paper, we study how to boost novelty for biomedical information retrieval through probabilistic latent semantic analysis. We conduct the study based on TREC Genomics Track data. In TREC Genomics Track, each topic is considered to have an arbitrary number of aspects, and the novelty of a piece of information retrieved, called a passage, is assessed based on the amount of new aspects it contains. In particular, the aspect performance of a ranked list is rewarded by the number of new aspects reached at each rank and penalized by the amount of irrelevant passages that are rated higher than the novel ones. Therefore, to improve aspect performance, we should reach as many aspects as possible and as early as possible. In this paper, we make a preliminary study on how probabilistic latent semantic analysis can help capture different aspects of a ranked list, and improve its performance by re-ranking. Experiments indicate that the proposed approach can greatly improve the aspect-level performance over baseline algorithm Okapi BM25.

Clinical information retrieval (IR) presents several challenges including terminology mismatch and granularity mismatch. One of the main objectives in clinical IR is to fill the semantic gap among the queries and documents and go beyond keywords matching. To address these issues, in this paper we attempt to use semantic information to improve the performance of clinical IR systems by representing queries in an expressive and meaningful context. To model a query context initially we model and develop query domain ontology. The query domain ontology represents concepts closely related with query concepts. Query context represents concepts extracted from query domain ontology and weighted according to their semantic relatedness to query concept(s). The query context is then exploited in query expansion and patients records re-ranking for improving clinical retrieval performance. We evaluate our approach on the TREC Medical Records dataset. Results show that our proposed approach significantly improves the retrieval performance compare to classic keyword-based IR model.

Patent prior art search is a task in patent retrieval where the goal is to rank documents which describe prior art work related to a patent application. One of the main properties of patent retrieval is that the query topic is a full patent application and does not represent a focused information need. This query by document nature of patent retrieval introduces new challenges and requires new investigations specific to this problem. Researchers have addressed this problem by considering different information resources for query reduction and query disambiguation. However, previous work has not fully studied the effect of using proximity information and exploiting domain specific resources for performing query disambiguation.

The explosive growth of geographic and temporal data has attracted much attention in information retrieval (IR) field. Since geographic and temporal information are often available in unstructured text, the IR task becomes a non-straightforward process. In this article, we propose a novel geo-temporal context mining approach and a geo-temporal ranking model for improving the search performance. Queries target implicitly ‘what’, ‘when’ and ‘where’ components. We model geographic and temporal query-dependent frequent patterns, called contexts. These contexts are derived based on extracting and ranking geographic and temporal entities found in pseudo-relevance feedback documents. Two methods are proposed for inferring the query-dependent contexts: (1) a frequency-based statistical approach and (2) a frequent pattern mining approach using a support threshold. The derived geographic and temporal query contexts are then exploited into a probabilistic ranking model. Finally, geographic, temporal and content-based scores are combined together for improving the geo-temporal search performance. We evaluate our approach on the New York Times news collection. The experimental results show that our proposed approach outperforms significantly a well-known baseline search, namely the probabilistic BM25 ranking model and state-of-the-art approaches in the field as well.

Traditional information retrieval (IR) systems show significant limitations on returning relevant documents that satisfy the user's information needs. In particular, to answer geographic and temporal user queries, the IR task becomes a nonstraightforward process where the available geographic and temporal information is often unstructured. In this article, we propose a geotemporal search approach that consists of modeling and exploiting geographic and temporal query context evidence that refers to implicit multivarying geographic and temporal intents behind the query. Modeling geographic and temporal query contexts is based on extracting and ranking geographic and temporal keywords found in pseudo‐relevant feedback (PRF) documents for a given query. Our geotemporal search approach is based on exploiting the geographic and temporal query contexts separately into a probabilistic ranking model and jointly into a proximity ranking model. Our hypothesis is based on the concept that geographic and temporal expressions tend to co‐occur within the document where the closer they are in the document, the more relevant the document is. Finally, geographic, temporal, and proximity scores are combined according to a linear combination formula. An extensive experimental evaluation conducted on a portion of the New York Times news collection and the TREC 2004 robust retrieval track collection shows that our geotemporal approach outperforms significantly a well‐known baseline search and the best known geotemporal search approaches in the domain. Finally, an in‐depth analysis shows a positive correlation between the geographic and temporal query sensitivity and the retrieval performance. Also, we find that geotemporal distance has a positive impact on retrieval performance generally.

In this paper, we propose a survival modeling approach to promoting ranking diversity for biomedical information retrieval. The proposed approach concerns with finding relevant documents that can deliver more different aspects of a query. First, two probabilistic models derived from the survival analysis theory are proposed for measuring aspect novelty. Second, a new method using Wikipedia to detect aspects covered by retrieved documents is presented. Third, an aspect filter based on a two-stage model is introduced. It ranks the detected aspects in decreasing order of the probability that an aspect is generated by the query. Finally, the relevance and the novelty of retrieved documents are combined at the aspect level for reranking. Experiments conducted on the TREC 2006 and 2007 Genomics collections demonstrate the effectiveness of the proposed approach in promoting ranking diversity for biomedical information retrieval. Moreover, we further evaluate our approach in the Web retrieval environment. The evaluation results on the ClueWeb09-T09B collection show that our approach can achieve promising performance improvements.

Rocchio's relevance feedback model is a classic query expansion method and it has been shown to be effective in boosting information retrieval performance. The selection of expansion terms in this method, however, does not take into account the relationship between the candidate terms and the query terms (e.g., term proximity). Intuitively, the proximity between candidate expansion terms and query terms can be exploited in the process of query expansion, since terms closer to query terms are more likely to be related to the query topic. In this paper, we study how to incorporate proximity information into the Rocchio's model, and propose a proximity-based Rocchio's model, called PRoc, with three variants. In our PRoc models, a new concept (proximity-based term frequency, ptf) is introduced to model the proximity information in the pseudo relevant documents, which is then used in three kinds of proximity measures. Experimental results on TREC collections show that our proposed PRoc models are effective and generally superior to the state-of-the-art relevance feedback models with optimal parameters.A direct comparison with positional relevance model (PRM) on the GOV2 collection also indicates our proposed model is at least competitive to the most recent progress.

Many information retrieval (IR) techniques have been proposed to improve the performance, and some combinations of these techniques has been demonstrated to be effective. However, how to effectively combine them is largely unexplored. It is possible that a method reduces the positive influence of the other one even if both of them are effective separately. In this paper, we propose a new hybrid model which can simply and flexibly combine components of three different IR techniques under a uniform framework. Extensive experiments on the TREC standard collections indicate that our proposed model can outperform the best TREC systems consistently in the ad-hoc retrieval. It shows that the combination strategy in our proposed model is very effective. Meanwhile, this method is also re-useable for other researchers to test whether their new methods are additive to the current technologies.

We investigate the effect of rewarding terms according to their locations in documents for probabilistic information retrieval. The intuition behind our approach is that a large amount of authors would summarize their ideas in some particular parts of documents. In this paper, we focus on the beginning part of documents. Several shape functions are defined to simulate the influence of term location information. We propose a Reward Term Retrieval model that combines the reward terms' information with BM25 to enhance probabilistic information retrieval performance.

Wikipedia is characterized by its dense link structure and a large number of articles in different languages, which make it a notableWeb corpus for knowledge extraction and mining, in particular for mining the multilingual associations. In this paper, motivated by a psychological theory of word meaning, we propose a graph‐based approach to constructing a cross‐language association dictionary (CLAD) fromWikipedia, which can be used in a variety of cross‐language accessing and processing applications. In order to evaluate the quality of the minedCLAD, and to demonstrate how the minedCLADcan be used in practice, we explore two different applications of the minedCLADto cross‐language information retrieval (CLIR). First, we use the minedCLADto conduct cross‐language query expansion; and, second, we use it to filter out translation candidates with low translation probabilities. Experimental results on a variety of standardCLIRtest collections show that theCLIRretrieval performance can be substantially improved with the above two applications ofCLAD, which indicates that the minedCLADis of sound quality.

Posting reviews online has become an increasingly popular way for people to express opinions and sentiments toward the products bought or services received. Analyzing the large volume of online reviews available would produce useful actionable knowledge that could be of economic values to vendors and other interested parties. In this paper, we conduct a case study in the movie domain, and tackle the problem of mining reviews for predicting product sales performance. Our analysis shows that both the sentiments expressed in the reviews and the quality of the reviews have a significant impact on the future sales performance of products in question. For the sentiment factor, we propose Sentiment PLSA (S-PLSA), in which a review is considered as a document generated by a number of hidden sentiment factors, in order to capture the complex nature of sentiments. Training an S-PLSA model enables us to obtain a succinct summary of the sentiment information embedded in the reviews. Based on S-PLSFA, we propose ARSA, an Autoregressive Sentiment-Aware model for sales prediction. We then seek to further improve the accuracy of prediction by considering the quality factor, with a focus on predicting the quality of a review in the absence of user-supplied indicators, and present ARSQA, an Autoregressive Sentiment and Quality Aware model, to utilize sentiments and quality for predicting product sales performance. Extensive experiments conducted on a large movie data set confirm the effectiveness of the proposed approach.

Term proximity retrieval rewards a document where the matched query terms occur close to each other. Although term proximity is known to be effective in many Information Retrieval (IR) applications, the within-document distribution of each individual query term and how the query terms associate with each other, are not fully considered. In this paper, we introduce a pseudo term, namely Cross Term, to model term proximity for boosting retrieval performance. An occurrence of a query term is assumed to have an impact towards its neighboring text, which gradually weakens with the increase of the distance to the place of occurrence. We use a shape function to characterize such an impact. A Cross Term occurs when two query terms appear close to each other and their impact shape functions have an intersection. We propose a Cross Term Retrieval (CRTER) model that combines the Cross Terms' information with basic probabilistic weighting models to rank the retrieved documents. Extensive experiments on standard TREC collections illustrate the effectiveness of our proposed CRTER model.

Classical probabilistic information retrieval (IR) models, e.g. BM25, deal with document length based on a trade-off between the Verbosity hypothesis, which assumes the independence of a document's relevance of its length, and the Scope hypothesis, which assumes the opposite. Despite the effectiveness of the classical probabilistic models, the potential relationship between document length and relevance is not fully explored to improve retrieval performance. In this paper, we conduct an in-depth study of this relationship based on the Scope hypothesis that document length does have its impact on relevance. We study a list of probability density functions and examine which of the density functions fits the best to the actual distribution of the document length. Based on the studied probability density functions, we propose a length-based BM25 relevance weighting model, called BM25L, which incorporates document length as a substantial weighting factor. Extensive experiments conducted on standard TREC collections show that our proposed BM25L markedly outperforms the original BM25 model, even if the latter is optimized.

Abstract Pseudo‐relevance feedback (PRF) via query expansion (QE) assumes that the top‐ranked documents from the first‐pass retrieval are relevant. The most informative terms in the pseudo‐relevant feedback documents are then used to update the original query representation in order to boost the retrieval performance. Most current PRF approaches estimate the importance of the candidate expansion terms based on their statistics on document level. However, a document for PRF may consist of different topics, which may not be all related to the query even if the document is judged relevant. The main argument of this article is the proposal to conduct PRF on a granularity smaller than on the document level. In this article, we propose a topic‐based feedback model with three different strategies for finding a good query‐related topic based on the Latent Dirichlet Allocation model. The experimental results on four representative TREC collections show that QE based on the derived topic achieves statistically significant improvements over a strong feedback model in the language modeling framework, which updates the query representation based on the top‐ranked documents.

their patients' records from paper to computer, enormous amounts of electronic medical records (EMR) have become available for medical research. Some of the EMR data are well-structured, for which traditional database management systems can provide effective retrieval and management functions. However, most of the EMR data (such as progress notes and consultation letters) are in free text formats. How to effectively and efficiently retrieve and discover useful information from the vast amount of such semi-structured data is a challenge faced by medical professionals. Without proper tools, the rich information and knowledge buried in the medical health records are unavailable for clinical research and decision-making. The objective of our research is to develop text analytics tools that are capable of parsing clinical medical data so that predefined search subjects that correspond to a list of medical diagnoses can be extracted. In addition to this particular core functionality, it is also desired that several important assets should be present within the text-analytics tools in order to improve its overall ability to be used as recommendation tools. In this research, we work with research scientists at the Institute for Clinical Evaluative Sciences (ICES) in Toronto and examine a number of techniques for structuring and processing free text documents in order to effectively and efficiently search and analyze vast amount of medical records. We implement several powerful medical text analytics tools for clinical data searching and classification. For data classification, our tools sort through a great amount of patientrecords to identify the likelihood of a patient having myocardial infarction (MI) or hypertension (HTN), and classify the patients accordingly. Our tools can also identify the likelihood of a patient being a smoker, previous smoker or non-smoker based on the text data of medical records.

Analyzing the large volume of online reviews would produce useful knowledge that could be of economic values to vendors and other interested parties. In particular, the sentiments expressed in the online reviews have been shown to be strongly correlated with the sales performance of products. In this paper, we present an adaptive sentiment analysis model called S-PLSA+, which aims to capture the hidden sentiment factors in the reviews with the capability to be incrementally updated as more data become available. We show how S-PLSA+ can be applied to sales performance prediction using an ARSA model developed in previous literature. A case study is conducted in the movie domain, and results from preliminary experiments confirm the effectiveness of the proposed model.

In this paper, we propose a probabilistic survival model derived from the survival analysis theory for measuring aspect novelty. The retrieved documents' query-relevance and novelty are combined at the aspect level for re-ranking. Experiments conducted on the TREC 2006 and 2007 Genomics collections demonstrate the effectiveness of the proposed approach in promoting ranking diversity for biomedical information retrieval.

Writing and publishing reviews online has become an increasingly popular way for people to express opinions and sentiments. Analyzing the large volume of online reviews available can produce useful knowledge that are of interest to vendors and other parties. Prior studies in the literature have shown that online reviews have a significant correlation with the sales of products, and therefore mining the reviews could help predict the sales performance of relevant products. However, those studies fail to consider one important factor that may significantly affect the accuracy of the prediction, i.e., the quality of the reviews. In this paper, we propose a regression model that explicitly takes into account the quality factor, and discusses how this quality information can be predicted when it is not readily available. Experimental results on a movie review dataset confirm the effectiveness of the proposed model.

In this paper, we present a framework for mining diverging patterns, a new type of contrast patterns whose frequency changes significantly differently in two data sets, e.g., it changes from a relatively low to a relatively high value in one dataset, but from high to low in the other. In this framework, a measure called diverging ratio is defined and used to discover diverging patterns. We use a four-dimensional vector to represent a pattern, and define the pattern's diverging ratio based on the angular difference between its vectors in two datasets. An algorithm is proposed to mine diverging patterns from a pair of datasets, which makes use of a standard frequent pattern mining algorithm to compute vector components efficiently. We demonstrate the effectiveness of our approach on real-world datasets, showing that the method can reveal novel knowledge from large databases.

In this paper, we propose a Bayesian learning approach to promoting diversity for information retrieval in biomedicine and a re-ranking model to improve retrieval performance in the biomedical domain. First, the re-ranking model computes the maximum posterior probability of the hidden property corresponding to each retrieved passage. Then it iteratively groups the passages into subsets according to their properties. Finally, these passages are re-ranked from the subsets as our output. There is no need for our proposed method to use any external biomedical resource. We evaluate our Bayesian learning approach by conducting extensive experiments on the TREC 2004-2007 Genomics data sets. The experimental results show the effectiveness of the proposed Bayesian learning approach for promoting diversity in ranking for biomedical information retrieval on four years TREC data sets.

In this paper, we propose a graph-based approach to constructing a multilingual association dictionary from Wikipedia, in which we exploit two kinds of links in Wikipedia articles to associate multilingual words and concepts together in a graph. The mined association dictionary is applied in cross language information retrieval (CLIR) to verify its quality. We evaluate our approach on four CLIR data sets and the experimental results show that it is possible to mine a good multilingual association dictionary from Wikipedia articles.

We argue that expert finding is sensitive to multiple document features in an organization, and therefore, can benefit from the incorporation of these document features. We propose a unified language model, which integrates multiple document features, namely, multiple levels of associations, PageRank, indegree, internal document structure, and URL length. Our experiments on two TREC Enterprise Track collections, i.e., the W3C and CSIRO datasets, demonstrate that the natures of the two organizational intranets and two types of expert finding tasks, i.e., key contact finding for CSIRO and knowledgeable person finding for W3C, influence the effectiveness of different document features. Our work provides insights into which document features work for certain types of expert finding tasks, and helps design expert finding strategies that are effective for different scenarios.

Online reviews provide a valuable resource for potential customers to make purchase decisions. However, the sheer volume of available reviews as well as the large variations in the review quality present a big impediment to the effective use of the reviews, as the most helpful reviews may be buried in the large amount of low quality reviews. The goal of this paper is to develop models and algorithms for predicting the helpfulness of reviews, which provides the basis for discovering the most helpful reviews for given products. We first show that the helpfulness of a review depends on three important factors: the reviewerpsilas expertise, the writing style of the review, and the timeliness of the review. Based on the analysis of those factors, we present a nonlinear regression model for helpfulness prediction. Our empirical study on the IMDB movie reviews dataset demonstrates that the proposed approach is highly effective.

In this paper, we propose a reranking model to improve the aspect-level performance in the biomedical domain. This model iteratively computes the maximum hidden aspect for every retrieved passage and then reranks these passages from aspect subsets. The experimental results show the improvements of the aspect-level performance up to 27.14% for 2006 Genomics topics and 27.09% for 2007 Genomics topics.

With the flourish of the Internet, online review mining has attracted a lot of attention from the research community. However, compared to various well-studied sentiment analysis and opinion summarization problems, less effort has been made to analyze the quality of online reviews. The objective of this paper is to fill in this gap by automatically evaluating the "helpfulness" of reviews and consequently developing novel models to identify the most helpful reviews for a particular product. In particular, based on a thorough analysis of various factors that may affect the review quality, we propose HelpMeter, a nonlinear regression model for helpfulness prediction. Some preliminary experiments were conducted on a movie review data set, and the performance results confirm the superiority of the proposed method.

Due to its high popularity, Weblogs (or blogs in short) present a wealth of information that can be very helpful in assessing the general public's sentiments and opinions. In this paper, we study the problem of mining sentiment information from blogs and investigate ways to use such information for predicting product sales performance. Based on an analysis of the complex nature of sentiments, we propose Sentiment PLSA (S-PLSA), in which a blog entry is viewed as a document generated by a number of hidden sentiment factors. Training an S-PLSA model on the blog data enables us to obtain a succinct summary of the sentiment information embedded in the blogs. We then present ARSA, an autoregressive sentiment-aware model, to utilize the sentiment information captured by S-PLSA for predicting product sales performance. Extensive experiments were conducted on a movie data set. We compare ARSA with alternative models that do not take into account the sentiment information, as well as a model with a different feature selection method. Experiments confirm the effectiveness and superiority of the proposed approach.

With the ever-increasing growth of data and information, finding the right knowledge becomes a real challenge and an urgent task. Traditional data and information retrieval systems that support the current web are no longer adequate for knowledge seeking tasks. Knowledge retrieval systems will be the next generation of retrieval system serving those purposes. Basic issues of knowledge retrieval systems are examined and a conceptual framework of such systems is proposed. Theories and Technologies such as theory of knowledge, machine learning and knowledge discovery, psychology, logic and inference, linguistics, etc. are briefly mentioned for the implementation of knowledge retrieval systems. Two applications of knowledge retrieval in rough sets and biomedical domains are presented.

Abstract With more and more information available on the Internet, the task of making personalized recommendations to assist the user's navigation has become increasingly important. Considering there might be millions of users with different backgrounds accessing a Web site everyday, it is infeasible to build a separate recommendation system for each user. To address this problem, clustering techniques can first be employed to discover user groups. Then, user navigation patterns for each group can be discovered, to allow the adaptation of a Web site to the interest of each individual group. In this paper, we propose to model user access sequences as stochastic processes, and a mixture of Markov models based approach is taken to cluster users and to capture the sequential relationships inherent in user access histories. Several important issues that arise in constructing the Markov models are also addressed. The first issue lies in the complexity of the mixture of Markov models. To improve the efficiency of building/maintaining the mixture of Markov models, we develop a lightweight adapt‐ive algorithm to update the model parameters without recomputing model parameters from scratch. The second issue concerns the proper selection of training data for building the mixture of Markov models. We investigate two different training data selection strategies and perform extensive experiments to compare their effectiveness on a real dataset that is generated by a Web‐based knowledge management system, Livelink.

In this paper, we investigate the use of data mining, in particular the text classification and co-training techniques, to identify more relevant passages based on a small set of labeled passages obtained from the blind feedback of a retrieval system. The data mining results are used to expand query terms and to re-estimate some of the parameters used in a probabilistic weighting function. We evaluate the data mining based feedback method on the TREC HARD data set. The results show that data mining can be successfully applied to improve the text retrieval performance. We report our experimental findings in detail.

We present an extensible java-based platform for contextual retrieval based on the probabilistic information retrieval model. Modules for dual indexes, relevance feedback with blind or machine learning approaches and query expansion with context are integrated into the Okapi system to deal with the contextual information. This platform allows easy extension to include other types of contextual information.

One challenging problem for biomedical text retrieval is to find accurate synonyms or name variants for biomedical entities. In this paper, we propose a new concept-based approach to tackle this problem. In this approach, a set of concepts instead of keywords will be extracted from a query first. Then these concepts will be used for retrieval purpose. The experiment results show that the proposed approach can boost the retrieval performance and it generates very good results on 2005 TREC Genomics data sets.

In this paper, we propose a dual index model for contextual IR. For each query, we search against both document level and passage level indexes, and use the corresponding merge function to update the weights for both documents and paragraphs by combining the results from both indexes according to the granularity information in metadata. Experiments on 2004 TREC data show that a significant improvement can be made by using the dual index model.

The problem of modeling and predicting a Web surfer's browsing patterns has gained increasing attention in recent years. In this paper we present our experience in clustering Web surfers using a mixture of Markov models with a real application of Livelink log data. We propose different techniques to improve the clustering performance, and evaluate the techniques through experiments.

Abstract We present a novel session identification method based on statistical language modeling. Unlike standard timeout methods, which use fixed time thresholds for session identification, we use an information theoretic approach that yields more robust results for identifying session boundaries. We evaluate our new approach by learning interesting association rules from the segmented session files. We then compare the performance of our approach to three standard session identification methods—the standard timeout method, the reference length method, and the maximal forward reference method—and find that our statistical language modeling approach generally yields superior results. However, as with every method, the performance of our technique varies with changing parameter settings. Therefore, we also analyze the influence of the two key factors in our language‐modeling–based approach: the choice of smoothing technique and the language model order. We find that all standard smoothing techniques, save one, perform well, and that performance is robust to language model order.

We propose two algorithms for grouping and summarizing association rules. The first algorithm recursively groups rules according to the structure of the rules and generates a tree of clusters as a result. The second algorithm groups the rules according to the semantic distance between the rules by making use of an automatically tagged semantic tree-structured network of items. We provide a case study in which the proposed algorithms are evaluated. The results show that our grouping methods are effective and produce good grouping results.

Livelink is a collaborative intranet, extranet and e-business application that enables employees and business partners of an organization to capture, share and reuse business information and knowledge. The usage of the Livelink software has been recorded by the Livelink Web server in its log files. We present an application of data mining techniques to the Livelink Web usage data. In particular, we focus on how to find interesting association rules and sequential patterns from the Livelink log files. A number of interestingness measures are used in our application to identify interesting rules and patterns. We present a comparison of these measures based on the feedback from domain experts. Some of the interestingness measures are found to be better than others.

We present our experience in mining web usage patterns from a large collection of Livelink log data. Livelink is a web-based product of Open Text, which provides automatic management and retrieval of different types of information objects over an intranet or extranet. We report our experience in preprocessing raw log data and post-processing the mining results for finding interesting rules. In particular we compare and evaluate a number of rule interestingness measures and find that two of the measures that have not been used in association rule learning work very well.

We propose a self-supervised word-segmentation technique for Chinese information retrieval. This method combines the advantages of traditional dictionary based approaches with character based approaches, while overcoming many of their shortcomings. Experiments on TREC data show comparable performance to both the dictionary based and the character based approaches. However, our method is language independent and unsupervised, which provides a promising avenue for constructing accurate multilingual information retrieval systems that are flexible and adaptive.