Jamie Callan

Zhengbao Jiang, Luyu Gao, Jun Araki et al. · cmu

Systems for knowledge-intensive tasks such as open-domain question answering (QA) usually consist of two stages: efficient retrieval of relevant documents from a large corpus and detailed reading of the selected documents to generate answers. Retrievers and readers are usually modeled separately, which necessitates a cumbersome implementation and is hard to train and adapt in an end-to-end fashion. In this paper, we revisit this design and eschew the separate architecture and training in favor of a single Transformer that performs Retrieval as Attention (ReAtt), and end-to-end training solely based on supervision from the end QA task. We demonstrate for the first time that a single model trained end-to-end can achieve both competitive retrieval and QA performance, matching or slightly outperforming state-of-the-art separately trained retrievers and readers. Moreover, end-to-end adaptation significantly boosts its performance on out-of-domain datasets in both supervised and unsupervised settings, making our model a simple and adaptable solution for knowledge-intensive tasks. Code and models are available at https://github.com/jzbjyb/ReAtt.

Luyu Gao, Aman Madaan, Shuyan Zhou et al. · cmu

Large language models (LLMs) have recently demonstrated an impressive ability to perform arithmetic and symbolic reasoning tasks, when provided with a few examples at test time ("few-shot prompting"). Much of this success can be attributed to prompting methods such as "chain-of-thought'', which employ LLMs for both understanding the problem description by decomposing it into steps, as well as solving each step of the problem. While LLMs seem to be adept at this sort of step-by-step decomposition, LLMs often make logical and arithmetic mistakes in the solution part, even when the problem is decomposed correctly. In this paper, we present Program-Aided Language models (PAL): a novel approach that uses the LLM to read natural language problems and generate programs as the intermediate reasoning steps, but offloads the solution step to a runtime such as a Python interpreter. With PAL, decomposing the natural language problem into runnable steps remains the only learning task for the LLM, while solving is delegated to the interpreter. We demonstrate this synergy between a neural LLM and a symbolic interpreter across 13 mathematical, symbolic, and algorithmic reasoning tasks from BIG-Bench Hard and other benchmarks. In all these natural language reasoning tasks, generating code using an LLM and reasoning using a Python interpreter leads to more accurate results than much larger models. For example, PAL using Codex achieves state-of-the-art few-shot accuracy on the GSM8K benchmark of math word problems, surpassing PaLM-540B which uses chain-of-thought by absolute 15% top-1. Our code and data are publicly available at http://reasonwithpal.com/ .

Luyu Gao, Xueguang Ma, Jimmy Lin et al. · cmu

While dense retrieval has been shown effective and efficient across tasks and languages, it remains difficult to create effective fully zero-shot dense retrieval systems when no relevance label is available. In this paper, we recognize the difficulty of zero-shot learning and encoding relevance. Instead, we propose to pivot through Hypothetical Document Embeddings~(HyDE). Given a query, HyDE first zero-shot instructs an instruction-following language model (e.g. InstructGPT) to generate a hypothetical document. The document captures relevance patterns but is unreal and may contain false details. Then, an unsupervised contrastively learned encoder~(e.g. Contriever) encodes the document into an embedding vector. This vector identifies a neighborhood in the corpus embedding space, where similar real documents are retrieved based on vector similarity. This second step ground the generated document to the actual corpus, with the encoder's dense bottleneck filtering out the incorrect details. Our experiments show that HyDE significantly outperforms the state-of-the-art unsupervised dense retriever Contriever and shows strong performance comparable to fine-tuned retrievers, across various tasks (e.g. web search, QA, fact verification) and languages~(e.g. sw, ko, ja).

Luyu Gao, Xueguang Ma, Jimmy Lin et al. · cmu

Recent rapid advancements in deep pre-trained language models and the introductions of large datasets have powered research in embedding-based dense retrieval. While several good research papers have emerged, many of them come with their own software stacks. These stacks are typically optimized for some particular research goals instead of efficiency or code structure. In this paper, we present Tevatron, a dense retrieval toolkit optimized for efficiency, flexibility, and code simplicity. Tevatron provides a standardized pipeline for dense retrieval including text processing, model training, corpus/query encoding, and search. This paper presents an overview of Tevatron and demonstrates its effectiveness and efficiency across several IR and QA data sets. We also show how Tevatron's flexible design enables easy generalization across datasets, model architectures, and accelerator platforms(GPU/TPU). We believe Tevatron can serve as an effective software foundation for dense retrieval system research including design, modeling, and optimization.

Arnold Overwijk, Chenyan Xiong, Xiao Liu et al. · cmu

ClueWeb22, the newest iteration of the ClueWeb line of datasets, provides 10 billion web pages affiliated with rich information. Its design was influenced by the need for a high quality, large scale web corpus to support a range of academic and industry research, for example, in information systems, retrieval-augmented AI systems, and model pretraining. Compared with earlier ClueWeb corpora, the ClueWeb22 corpus is larger, more varied, of higher-quality, and aligned with the document distributions in commercial web search. Besides raw HTML, ClueWeb22 includes rich information about the web pages provided by industry-standard document understanding systems, including the visual representation of pages rendered by a web browser, parsed HTML structure information from a neural network parser, and pre-processed cleaned document text to lower the barrier to entry. Many of these signals have been widely used in industry but are available to the research community for the first time at this scale.

Luyu Gao, Jamie Callan · cmu

Long document re-ranking has been a challenging problem for neural re-rankers based on deep language models like BERT. Early work breaks the documents into short passage-like chunks. These chunks are independently mapped to scalar scores or latent vectors, which are then pooled into a final relevance score. These encode-and-pool methods however inevitably introduce an information bottleneck: the low dimension representations. In this paper, we propose instead to model full query-to-document interaction, leveraging the attention operation and modular Transformer re-ranker framework. First, document chunks are encoded independently with an encoder module. An interaction module then encodes the query and performs joint attention from the query to all document chunk representations. We demonstrate that the model can use this new degree of freedom to aggregate important information from the entire document. Our experiments show that this design produces effective re-ranking on two classical IR collections Robust04 and ClueWeb09, and a large-scale supervised collection MS-MARCO document ranking.

Minyang Tian, Luyu Gao, Shizhuo Dylan Zhang et al. · princeton, uw

Since language models (LMs) now outperform average humans on many challenging tasks, it has become increasingly difficult to develop challenging, high-quality, and realistic evaluations. We address this issue by examining LMs' capabilities to generate code for solving real scientific research problems. Incorporating input from scientists and AI researchers in 16 diverse natural science sub-fields, including mathematics, physics, chemistry, biology, and materials science, we created a scientist-curated coding benchmark, SciCode. The problems in SciCode naturally factorize into multiple subproblems, each involving knowledge recall, reasoning, and code synthesis. In total, SciCode contains 338 subproblems decomposed from 80 challenging main problems. It offers optional descriptions specifying useful scientific background information and scientist-annotated gold-standard solutions and test cases for evaluation. Claude3.5-Sonnet, the best-performing model among those tested, can solve only 4.6% of the problems in the most realistic setting. We believe that SciCode demonstrates both contemporary LMs' progress towards becoming helpful scientific assistants and sheds light on the development and evaluation of scientific AI in the future.

Jingjie Ning, João Coelho, Yibo Kong et al.

LLM-powered search agents are increasingly being used for multi-step information seeking tasks, yet the IR community lacks empirical understanding of how agentic search sessions unfold and how retrieved evidence is reflected in later queries. This paper presents a large-scale log analysis of agentic search based on 14.44M search requests (3.97M sessions) collected from DeepResearchGym, i.e., an open-source search API accessed by external agentic clients. We sessionize the logs, assign session-level intents and step-wise query-reformulation labels using LLM-based annotation, and propose Context-driven Term Adoption Rate (CTAR) to quantify whether newly introduced query terms are lexically traceable to previously retrieved evidence. Our analyses reveal distinctive behavioral patterns. First, over 90\% of multi-turn sessions contain at most ten steps, and 89\% of inter-step intervals fall under one minute. Second, behavior varies by intent. Fact-seeking sessions exhibit high repetition that increases over time, while sessions requiring reasoning sustain broader exploration. Third, query reformulations are often traceable to retrieved evidence across steps. On average, 54\% of newly introduced query terms appear in the accumulated evidence context, with additional traceability to earlier steps beyond the most recent retrieval. These findings provide candidate signals for repetition-aware stopping, intent-adaptive retrieval budgeting, and explicit cross-step context tracking. We released the anonymized logs, making them available at a public HuggingFace~\chref{https://huggingface.co/datasets/cx-cmu/deepresearchgym-agentic-search-logs}{repository}.

Zhengbao Jiang, Frank F. Xu, Luyu Gao et al.

Despite the remarkable ability of large language models (LMs) to comprehend and generate language, they have a tendency to hallucinate and create factually inaccurate output. Augmenting LMs by retrieving information from external knowledge resources is one promising solution. Most existing retrieval augmented LMs employ a retrieve-and-generate setup that only retrieves information once based on the input. This is limiting, however, in more general scenarios involving generation of long texts, where continually gathering information throughout generation is essential. In this work, we provide a generalized view of active retrieval augmented generation, methods that actively decide when and what to retrieve across the course of the generation. We propose Forward-Looking Active REtrieval augmented generation (FLARE), a generic method which iteratively uses a prediction of the upcoming sentence to anticipate future content, which is then utilized as a query to retrieve relevant documents to regenerate the sentence if it contains low-confidence tokens. We test FLARE along with baselines comprehensively over 4 long-form knowledge-intensive generation tasks/datasets. FLARE achieves superior or competitive performance on all tasks, demonstrating the effectiveness of our method. Code and datasets are available at https://github.com/jzbjyb/FLARE.

Cameron VandenBerg, Jamie Callan

Text mining and analytics software has become popular, but little attention has been paid to the software architectures of such systems. Often they are built from scratch using special-purpose software and data structures, which increases their cost and complexity. This demo paper describes Sifaka, a new open-source text mining application constructed above a standard search engine index using existing application programmer interface (API) calls. Indexing integrates popular annotation software libraries to augment the full-text index with noun phrase and named-entities; n-grams are also provided. Sifaka enables a person to quickly explore and analyze large text collections using search, frequency analysis, and co-occurrence analysis; and import existing document labels or interactively construct document sets that are positive or negative examples of new concepts, perform feature selection, and export feature vectors compatible with popular machine learning software. Sifaka demonstrates that search engines are good platforms for text mining applications while also making common IR text mining capabilities accessible to researchers in disciplines where programming skills are less common.

João Coelho, Bruno Martins, João Magalhães et al.

This study investigates the existence of positional biases in Transformer-based models for text representation learning, particularly in the context of web document retrieval. We build on previous research that demonstrated loss of information in the middle of input sequences for causal language models, extending it to the domain of representation learning. We examine positional biases at various stages of training for an encoder-decoder model, including language model pre-training, contrastive pre-training, and contrastive fine-tuning. Experiments with the MS-MARCO document collection reveal that after contrastive pre-training the model already generates embeddings that better capture early contents of the input, with fine-tuning further aggravating this effect.

Jingjie Ning, Yibo Kong, Yunfan Long et al.

Retrieval-Augmented Generation (RAG) couples document retrieval with large language models (LLMs). While scaling generators improves accuracy, it also raises cost and limits deployability. We explore an orthogonal axis: enlarging the retriever's corpus to reduce reliance on large LLMs. Experimental results show that corpus scaling consistently strengthens RAG and can often serve as a substitute for increasing model size, though with diminishing returns at larger scales. Small- and mid-sized generators paired with larger corpora often rival much larger models with smaller corpora; mid-sized models tend to gain the most, while tiny and large models benefit less. Our analysis shows that improvements arise primarily from increased coverage of answer-bearing passages, while utilization efficiency remains largely unchanged. These findings establish a principled corpus-generator trade-off: investing in larger corpora offers an effective path to stronger RAG, often comparable to enlarging the LLM itself.

Luyu Gao, Yunyi Zhang, Jamie Callan

Long-context modeling is one of the critical capabilities of language AI for digesting and reasoning over complex information pieces. In practice, long-context capabilities are typically built into a pre-trained language model~(LM) through a carefully designed context extension stage, with the goal of producing generalist long-context capabilities. In our preliminary experiments, however, we discovered that the current open-weight generalist long-context models are still lacking in practical long-context processing tasks. While this means perfectly effective long-context modeling demands task-specific data, the cost can be prohibitive. In this paper, we draw inspiration from how humans process a large body of information: a lossy \textbf{retrieval} stage ranks a large set of documents while the reader ends up reading deeply only the top candidates. We build an \textbf{automatic} data synthesis pipeline that mimics this process using short-context LMs. The short-context LMs are further tuned using these self-generated data to obtain task-specific long-context capabilities. Similar to how pre-training learns from imperfect data, we hypothesize and further demonstrate that the short-context model can bootstrap over the synthetic data, outperforming not only long-context generalist models but also the retrieval and read pipeline used to synthesize the training data in real-world tasks such as long-context retrieval augmented generation.

HongChien Yu, Chenyan Xiong, Jamie Callan

Dense retrieval systems conduct first-stage retrieval using embedded representations and simple similarity metrics to match a query to documents. Its effectiveness depends on encoded embeddings to capture the semantics of queries and documents, a challenging task due to the shortness and ambiguity of search queries. This paper proposes ANCE-PRF, a new query encoder that uses pseudo relevance feedback (PRF) to improve query representations for dense retrieval. ANCE-PRF uses a BERT encoder that consumes the query and the top retrieved documents from a dense retrieval model, ANCE, and it learns to produce better query embeddings directly from relevance labels. It also keeps the document index unchanged to reduce overhead. ANCE-PRF significantly outperforms ANCE and other recent dense retrieval systems on several datasets. Analysis shows that the PRF encoder effectively captures the relevant and complementary information from PRF documents, while ignoring the noise with its learned attention mechanism.

Luyu Gao, Jamie Callan

Recent research demonstrates the effectiveness of using fine-tuned language models~(LM) for dense retrieval. However, dense retrievers are hard to train, typically requiring heavily engineered fine-tuning pipelines to realize their full potential. In this paper, we identify and address two underlying problems of dense retrievers: i)~fragility to training data noise and ii)~requiring large batches to robustly learn the embedding space. We use the recently proposed Condenser pre-training architecture, which learns to condense information into the dense vector through LM pre-training. On top of it, we propose coCondenser, which adds an unsupervised corpus-level contrastive loss to warm up the passage embedding space. Retrieval experiments on MS-MARCO, Natural Question, and Trivia QA datasets show that coCondenser removes the need for heavy data engineering such as augmentation, synthesis, or filtering, as well as the need for large batch training. It shows comparable performance to RocketQA, a state-of-the-art, heavily engineered system, using simple small batch fine-tuning.

Luyu Gao, Jamie Callan

Pre-trained Transformer language models (LM) have become go-to text representation encoders. Prior research fine-tunes deep LMs to encode text sequences such as sentences and passages into single dense vector representations for efficient text comparison and retrieval. However, dense encoders require a lot of data and sophisticated techniques to effectively train and suffer in low data situations. This paper finds a key reason is that standard LMs' internal attention structure is not ready-to-use for dense encoders, which needs to aggregate text information into the dense representation. We propose to pre-train towards dense encoder with a novel Transformer architecture, Condenser, where LM prediction CONditions on DENSE Representation. Our experiments show Condenser improves over standard LM by large margins on various text retrieval and similarity tasks.

Luyu Gao, Zhuyun Dai, Jamie Callan

Classical information retrieval systems such as BM25 rely on exact lexical match and carry out search efficiently with inverted list index. Recent neural IR models shifts towards soft semantic matching all query document terms, but they lose the computation efficiency of exact match systems. This paper presents COIL, a contextualized exact match retrieval architecture that brings semantic lexical matching. COIL scoring is based on overlapping query document tokens' contextualized representations. The new architecture stores contextualized token representations in inverted lists, bringing together the efficiency of exact match and the representation power of deep language models. Our experimental results show COIL outperforms classical lexical retrievers and state-of-the-art deep LM retrievers with similar or smaller latency.

Luyu Gao, Zhuyun Dai, Jamie Callan

Pre-trained deep language models~(LM) have advanced the state-of-the-art of text retrieval. Rerankers fine-tuned from deep LM estimates candidate relevance based on rich contextualized matching signals. Meanwhile, deep LMs can also be leveraged to improve search index, building retrievers with better recall. One would expect a straightforward combination of both in a pipeline to have additive performance gain. In this paper, we discover otherwise and that popular reranker cannot fully exploit the improved retrieval result. We, therefore, propose a Localized Contrastive Estimation (LCE) for training rerankers and demonstrate it significantly improves deep two-stage models.

Luís Borges, Bruno Martins, Jamie Callan

Our work aimed at experimentally assessing the benefits of model ensembling within the context of neural methods for passage reranking. Starting from relatively standard neural models, we use a previous technique named Fast Geometric Ensembling to generate multiple model instances from particular training schedules, then focusing or attention on different types of approaches for combining the results from the multiple model instances (e.g., averaging the ranking scores, using fusion methods from the IR literature, or using supervised learning-to-rank). Tests with the MS-MARCO dataset show that model ensembling can indeed benefit the ranking quality, particularly with supervised learning-to-rank although also with unsupervised rank aggregation.

HongChien Yu, Zhuyun Dai, Jamie Callan

Most research on pseudo relevance feedback (PRF) has been done in vector space and probabilistic retrieval models. This paper shows that Transformer-based rerankers can also benefit from the extra context that PRF provides. It presents PGT, a graph-based Transformer that sparsifies attention between graph nodes to enable PRF while avoiding the high computational complexity of most Transformer architectures. Experiments show that PGT improves upon non-PRF Transformer reranker, and it is at least as accurate as Transformer PRF models that use full attention, but with lower computational costs.

Luyu Gao, Yunyi Zhang, Jiawei Han et al.

Contrastive learning has been applied successfully to learn vector representations of text. Previous research demonstrated that learning high-quality representations benefits from batch-wise contrastive loss with a large number of negatives. In practice, the technique of in-batch negative is used, where for each example in a batch, other batch examples' positives will be taken as its negatives, avoiding encoding extra negatives. This, however, still conditions each example's loss on all batch examples and requires fitting the entire large batch into GPU memory. This paper introduces a gradient caching technique that decouples backpropagation between contrastive loss and the encoder, removing encoder backward pass data dependency along the batch dimension. As a result, gradients can be computed for one subset of the batch at a time, leading to almost constant memory usage.

Shuo Zhang, Krisztian Balog, Jamie Callan

Category systems are central components of knowledge bases, as they provide a hierarchical grouping of semantically related concepts and entities. They are a unique and valuable resource that is utilized in a broad range of information access tasks. To aid knowledge editors in the manual process of expanding a category system, this paper presents a method of generating categories for sets of entities. First, we employ neural abstractive summarization models to generate candidate categories. Next, the location within the hierarchy is identified for each candidate. Finally, structure-, content-, and hierarchy-based features are used to rank candidates to identify by the most promising ones (measured in terms of specificity, hierarchy, and importance). We develop a test collection based on Wikipedia categories and demonstrate the effectiveness of the proposed approach.

Vaibhav Kumar, Vikas Raunak, Jamie Callan

Given a natural language query, teaching machines to ask clarifying questions is of immense utility in practical natural language processing systems. Such interactions could help in filling information gaps for better machine comprehension of the query. For the task of ranking clarification questions, we hypothesize that determining whether a clarification question pertains to a missing entry in a given post (on QA forums such as StackExchange) could be considered as a special case of Natural Language Inference (NLI), where both the post and the most relevant clarification question point to a shared latent piece of information or context. We validate this hypothesis by incorporating representations from a Siamese BERT model fine-tuned on NLI and Multi-NLI datasets into our models and demonstrate that our best performing model obtains a relative performance improvement of 40 percent and 60 percent respectively (on the key metric of Precision@1), over the state-of-the-art baseline(s) on the two evaluation sets of the StackExchange dataset, thereby, significantly surpassing the state-of-the-art.

Luyu Gao, Zhuyun Dai, Jamie Callan

Deep language models such as BERT pre-trained on large corpus have given a huge performance boost to the state-of-the-art information retrieval ranking systems. Knowledge embedded in such models allows them to pick up complex matching signals between passages and queries. However, the high computation cost during inference limits their deployment in real-world search scenarios. In this paper, we study if and how the knowledge for search within BERT can be transferred to a smaller ranker through distillation. Our experiments demonstrate that it is crucial to use a proper distillation procedure, which produces up to nine times speedup while preserving the state-of-the-art performance.

Shuo Zhang, Zhuyun Dai, Krisztian Balog et al.

Tabular data provide answers to a significant portion of search queries. However, reciting an entire result table is impractical in conversational search systems. We propose to generate natural language summaries as answers to describe the complex information contained in a table. Through crowdsourcing experiments, we build a new conversation-oriented, open-domain table summarization dataset. It includes annotated table summaries, which not only answer questions but also help people explore other information in the table. We utilize this dataset to develop automatic table summarization systems as SOTA baselines. Based on the experimental results, we identify challenges and point out future research directions that this resource will support.

Luyu Gao, Zhuyun Dai, Tongfei Chen et al.

This paper presents CLEAR, a retrieval model that seeks to complement classical lexical exact-match models such as BM25 with semantic matching signals from a neural embedding matching model. CLEAR explicitly trains the neural embedding to encode language structures and semantics that lexical retrieval fails to capture with a novel residual-based embedding learning method. Empirical evaluations demonstrate the advantages of CLEAR over state-of-the-art retrieval models, and that it can substantially improve the end-to-end accuracy and efficiency of reranking pipelines.

Luyu Gao, Zhuyun Dai, Jamie Callan

Recent innovations in Transformer-based ranking models have advanced the state-of-the-art in information retrieval. However, these Transformers are computationally expensive, and their opaque hidden states make it hard to understand the ranking process. In this work, we modularize the Transformer ranker into separate modules for text representation and interaction. We show how this design enables substantially faster ranking using offline pre-computed representations and light-weight online interactions. The modular design is also easier to interpret and sheds light on the ranking process in Transformer rankers.

Jeffrey Dalton, Chenyan Xiong, Jamie Callan

The Conversational Assistance Track (CAsT) is a new track for TREC 2019 to facilitate Conversational Information Seeking (CIS) research and to create a large-scale reusable test collection for conversational search systems. The document corpus is 38,426,252 passages from the TREC Complex Answer Retrieval (CAR) and Microsoft MAchine Reading COmprehension (MARCO) datasets. Eighty information seeking dialogues (30 train, 50 test) are an average of 9 to 10 questions long. Relevance assessments are provided for 30 training topics and 20 test topics. This year 21 groups submitted a total of 65 runs using varying methods for conversational query understanding and ranking. Methods include traditional retrieval based methods, feature based learning-to-rank, neural models, and knowledge enhanced methods. A common theme through the runs is the use of BERT-based neural reranking methods. Leading methods also employed document expansion, conversational query expansion, and generative language models for conversational query rewriting (GPT-2). The results show a gap between automatic systems and those using the manually resolved utterances, with a 35% relative improvement of manual rewrites over the best automatic system.

Zhuyun Dai, Jamie Callan

Term frequency is a common method for identifying the importance of a term in a query or document. But it is a weak signal, especially when the frequency distribution is flat, such as in long queries or short documents where the text is of sentence/passage-length. This paper proposes a Deep Contextualized Term Weighting framework that learns to map BERT's contextualized text representations to context-aware term weights for sentences and passages. When applied to passages, DeepCT-Index produces term weights that can be stored in an ordinary inverted index for passage retrieval. When applied to query text, DeepCT-Query generates a weighted bag-of-words query. Both types of term weight can be used directly by typical first-stage retrieval algorithms. This is novel because most deep neural network based ranking models have higher computational costs, and thus are restricted to later-stage rankers. Experiments on four datasets demonstrate that DeepCT's deep contextualized text understanding greatly improves the accuracy of first-stage retrieval algorithms.

Zhuyun Dai, Jamie Callan

Neural networks provide new possibilities to automatically learn complex language patterns and query-document relations. Neural IR models have achieved promising results in learning query-document relevance patterns, but few explorations have been done on understanding the text content of a query or a document. This paper studies leveraging a recently-proposed contextual neural language model, BERT, to provide deeper text understanding for IR. Experimental results demonstrate that the contextual text representations from BERT are more effective than traditional word embeddings. Compared to bag-of-words retrieval models, the contextual language model can better leverage language structures, bringing large improvements on queries written in natural languages. Combining the text understanding ability with search knowledge leads to an enhanced pre-trained BERT model that can benefit related search tasks where training data are limited.

Flávio Martins, João Magalhães, Jamie Callan

Newsworthy events are broadcast through multiple mediums and prompt the crowds to produce comments on social media. In this paper, we propose to leverage on this behavioral dynamics to estimate the most relevant time periods for an event (i.e., query). Recent advances have shown how to improve the estimation of the temporal relevance of such topics. In this approach, we build on two major novelties. First, we mine temporal evidences from hundreds of external sources into topic-based external collections to improve the robustness of the detection of relevant time periods. Second, we propose a formal retrieval model that generalizes the use of the temporal dimension across different aspects of the retrieval process. In particular, we show that temporal evidence of external collections can be used to (i) infer a topic's temporal relevance, (ii) select the query expansion terms, and (iii) re-rank the final results for improved precision. Experiments with TREC Microblog collections show that the proposed time-aware retrieval model makes an effective and extensive use of the temporal dimension to improve search results over the most recent temporal models. Interestingly, we observe a strong correlation between precision and the temporal distribution of retrieved and relevant documents.

Flávio Martins, João Magalhães, Jamie Callan

In microblog retrieval, query expansion can be essential to obtain good search results due to the short size of queries and posts. Since information in microblogs is highly dynamic, an up-to-date index coupled with pseudo-relevance feedback (PRF) with an external corpus has a higher chance of retrieving more relevant documents and improving ranking. In this paper, we focus on the research question:how can we reduce the query expansion computational cost while maintaining the same retrieval precision as standard PRF? Therefore, we propose to accelerate the query expansion step of pseudo-relevance feedback. The hypothesis is that using an expansion corpus organized into verticals for expanding the query, will lead to a more efficient query expansion process and improved retrieval effectiveness. Thus, the proposed query expansion method uses a distributed search architecture and resource selection algorithms to provide an efficient query expansion process. Experiments on the TREC Microblog datasets show that the proposed approach can match or outperform standard PRF in MAP and NDCG@30, with a computational cost that is three orders of magnitude lower.

Mary Arpita Pyreddy, Varshini Ramaseshan, Narendra Nath Joshi et al.

This paper studies the consistency of the kernel-based neural ranking model K-NRM, a recent state-of-the-art neural IR model, which is important for reproducible research and deployment in the industry. We find that K-NRM has low variance on relevance-based metrics across experimental trials. In spite of this low variance in overall performance, different trials produce different document rankings for individual queries. The main source of variance in our experiments was found to be different latent matching patterns captured by K-NRM. In the IR-customized word embeddings learned by K-NRM, the query-document word pairs follow two different matching patterns that are equally effective, but align word pairs differently in the embedding space. The different latent matching patterns enable a simple yet effective approach to construct ensemble rankers, which improve K-NRM's effectiveness and generalization abilities.

Chenyan Xiong, Zhengzhong Liu, Jamie Callan et al.

This paper presents a Kernel Entity Salience Model (KESM) that improves text understanding and retrieval by better estimating entity salience (importance) in documents. KESM represents entities by knowledge enriched distributed representations, models the interactions between entities and words by kernels, and combines the kernel scores to estimate entity salience. The whole model is learned end-to-end using entity salience labels. The salience model also improves ad hoc search accuracy, providing effective ranking features by modeling the salience of query entities in candidate documents. Our experiments on two entity salience corpora and two TREC ad hoc search datasets demonstrate the effectiveness of KESM over frequency-based and feature-based methods. We also provide examples showing how KESM conveys its text understanding ability learned from entity salience to search.

Keyang Xu, Kyle Yingkai Gao, Jamie Callan

Existing techniques for efficiently crawling social media sites rely on URL patterns, query logs, and human supervision. This paper describes SOUrCe, a structure-oriented unsupervised crawler that uses page structures to learn how to crawl a social media site efficiently. SOUrCe consists of two stages. During its unsupervised learning phase, SOUrCe constructs a sitemap that clusters pages based on their structural similarity and generates a navigation table that describes how the different types of pages in the site are linked together. During its harvesting phase, it uses the navigation table and a crawling policy to guide the choice of which links to crawl next. Experiments show that this architecture supports different styles of crawling efficiently, and does a better job of staying focused on user-created contents than baseline methods.

Kyle Yingkai Gao, Jamie Callan

Tables are common and important in scientific documents, yet most text-based document search systems do not capture structures and semantics specific to tables. How to bridge different types of mismatch between keywords queries and scientific tables and what influences ranking quality needs to be carefully investigated. This paper considers the structure of tables and gives different emphasis to table components. On the query side, thanks to external knowledge such as knowledge bases and ontologies, key concepts are extracted and used to build structured queries, and target quantity types are identified and used to expand original queries. A probabilistic framework is proposed to incorporate structural and semantic information from both query and table sides. We also construct and release TableArXiv, a high quality dataset with 105 queries and corresponding relevance judgements for scientific table search. Experiments demonstrate significantly higher accuracy overall and at the top of the rankings than several baseline methods.

Chenyan Xiong, Jamie Callan, Tie-Yan Liu

This paper presents a word-entity duet framework for utilizing knowledge bases in ad-hoc retrieval. In this work, the query and documents are modeled by word-based representations and entity-based representations. Ranking features are generated by the interactions between the two representations, incorporating information from the word space, the entity space, and the cross-space connections through the knowledge graph. To handle the uncertainties from the automatically constructed entity representations, an attention-based ranking model AttR-Duet is developed. With back-propagation from ranking labels, the model learns simultaneously how to demote noisy entities and how to rank documents with the word-entity duet. Evaluation results on TREC Web Track ad-hoc task demonstrate that all of the four-way interactions in the duet are useful, the attention mechanism successfully steers the model away from noisy entities, and together they significantly outperform both word-based and entity-based learning to rank systems.

Chenyan Xiong, Zhuyun Dai, Jamie Callan et al.

This paper proposes K-NRM, a kernel based neural model for document ranking. Given a query and a set of documents, K-NRM uses a translation matrix that models word-level similarities via word embeddings, a new kernel-pooling technique that uses kernels to extract multi-level soft match features, and a learning-to-rank layer that combines those features into the final ranking score. The whole model is trained end-to-end. The ranking layer learns desired feature patterns from the pairwise ranking loss. The kernels transfer the feature patterns into soft-match targets at each similarity level and enforce them on the translation matrix. The word embeddings are tuned accordingly so that they can produce the desired soft matches. Experiments on a commercial search engine's query log demonstrate the improvements of K-NRM over prior feature-based and neural-based states-of-the-art, and explain the source of K-NRM's advantage: Its kernel-guided embedding encodes a similarity metric tailored for matching query words to document words, and provides effective multi-level soft matches.

Flávio Martins, João Magalhães, Jamie Callan

In Twitter, and other microblogging services, the generation of new content by the crowd is often biased towards immediacy: what is happening now. Prompted by the propagation of commentary and information through multiple mediums, users on the Web interact with and produce new posts about newsworthy topics and give rise to trending topics. This paper proposes to leverage on the behavioral dynamics of users to estimate the most relevant time periods for a topic. Our hypothesis stems from the fact that when a real-world event occurs it usually has peak times on the Web: a higher volume of tweets, new visits and edits to related Wikipedia articles, and news published about the event. In this paper, we propose a novel time-aware ranking model that leverages on multiple sources of crowd signals. Our approach builds on two major novelties. First, a unifying approach that given query q, mines and represents temporal evidence from multiple sources of crowd signals. This allows us to predict the temporal relevance of documents for query q. Second, a principled retrieval model that integrates temporal signals in a learning to rank framework, to rank results according to the predicted temporal relevance. Evaluation on the TREC 2013 and 2014 Microblog track datasets demonstrates that the proposed model achieves a relative improvement of 13.2% over lexical retrieval models and 6.2% over a learning to rank baseline.

Bhavana Dalvi, William W. Cohen, Jamie Callan

We describe a open-domain information extraction method for extracting concept-instance pairs from an HTML corpus. Most earlier approaches to this problem rely on combining clusters of distributionally similar terms and concept-instance pairs obtained with Hearst patterns. In contrast, our method relies on a novel approach for clustering terms found in HTML tables, and then assigning concept names to these clusters using Hearst patterns. The method can be efficiently applied to a large corpus, and experimental results on several datasets show that our method can accurately extract large numbers of concept-instance pairs.

Bhavana Dalvi, William W. Cohen, Jamie Callan

In multiclass semi-supervised learning (SSL), it is sometimes the case that the number of classes present in the data is not known, and hence no labeled examples are provided for some classes. In this paper we present variants of well-known semi-supervised multiclass learning methods that are robust when the data contains an unknown number of classes. In particular, we present an "exploratory" extension of expectation-maximization (EM) that explores different numbers of classes while learning. "Exploratory" SSL greatly improves performance on three datasets in terms of F1 on the classes with seed examples i.e., the classes which are expected to be in the data. Our Exploratory EM algorithm also outperforms a SSL method based non-parametric Bayesian clustering.