English
Related papers

Related papers: Denoising Table-Text Retrieval for Open-Domain Que…

200 papers

The data landscape is rich with structured data, often of high value to organizations, driving important applications in data analysis and machine learning. Recent progress in representation learning and generative models for such data has…

Information Retrieval · Computer Science 2025-05-20 Xingyu Ji , Parker Glenn , Aditya G. Parameswaran , Madelon Hulsebos

Large-scale multi-tenant retrieval systems generate extensive query logs but lack curated relevance labels for effective domain adaptation, resulting in substantial underutilized "dark data". This challenge is compounded by the high cost of…

Since a vast number of tables can be easily collected from web pages, spreadsheets, PDFs, and various other document types, a flurry of table pre-training frameworks have been proposed following the success of text and images, and they have…

Computation and Language · Computer Science 2022-05-02 Haoyu Dong , Zhoujun Cheng , Xinyi He , Mengyu Zhou , Anda Zhou , Fan Zhou , Ao Liu , Shi Han , Dongmei Zhang

Open-domain questions are likely to be open-ended and ambiguous, leading to multiple valid answers. Existing approaches typically adopt the rerank-then-read framework, where a reader reads top-ranking evidence to predict answers. According…

Computation and Language · Computer Science 2022-03-02 Zhihong Shao , Minlie Huang

The diversity of tables makes table detection a great challenge, leading to existing models becoming more tedious and complex. Despite achieving high performance, they often overfit to the table style in training set, and suffer from…

Computation and Language · Computer Science 2023-12-19 Yang Fan , Xiangping Wu , Qingcai Chen , Heng Li , Yan Huang , Zhixiang Cai , Qitian Wu

We describe the development, characteristics and availability of a test collection for the task of Web table retrieval, which uses a large-scale Web Table Corpora extracted from the Common Crawl. Since a Web table usually has rich context…

Information Retrieval · Computer Science 2021-05-07 Zhiyu Chen , Shuo Zhang , Brian D. Davison

Table retrieval, essential for accessing information through tabular data, is less explored compared to text retrieval. The row/column structure and distinct fields of tables (including titles, headers, and cells) present unique challenges.…

Information Retrieval · Computer Science 2025-03-05 Da Li , Keping Bi , Jiafeng Guo , Xueqi Cheng

Considerable research attention has been paid to table detection by developing not only rule-based approaches reliant on hand-crafted heuristics but also deep learning approaches. Although recent studies successfully perform table detection…

Machine Learning · Computer Science 2022-11-15 Hyebin Kwon , Joungbin An , Dongwoo Lee , Won-Yong Shin

Research in Document Intelligence and especially in Document Key Information Extraction (DocKIE) has been mainly solved as Token Classification problem. Recent breakthroughs in both natural language processing (NLP) and computer vision…

Computation and Language · Computer Science 2023-04-24 Laurent Lam , Pirashanth Ratnamogan , Joël Tang , William Vanhuffel , Fabien Caspani

More and more end-to-end text spotting methods based on Transformer architecture have demonstrated superior performance. These methods utilize a bipartite graph matching algorithm to perform one-to-one optimal matching between predicted…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Yu Xie , Qian Qiao , Jun Gao , Tianxiang Wu , Jiaqing Fan , Yue Zhang , Jielei Zhang , Huyang Sun

Despite strong performance on existing benchmarks, it remains unclear whether large language models can reason over genuinely novel scientific information. Most evaluations score end-to-end RAG pipelines, where reasoning is confounded with…

Document-level relation extraction (Doc-RE) aims to extract relations between entities across multiple sentences. Therefore, Doc-RE requires more comprehensive reasoning abilities like humans, involving complex cross-sentence interactions…

Computation and Language · Computer Science 2025-08-05 Chengcheng Mai , Yuxiang Wang , Ziyu Gong , Hanxiang Wang , Yihua Huang

Table structure recognition is necessary for a comprehensive understanding of documents. Tables in unstructured business documents are tough to parse due to the high diversity of layouts, varying alignments of contents, and the presence of…

Computer Vision and Pattern Recognition · Computer Science 2021-11-16 Sachin Raja , Ajoy Mondal , C V Jawahar

Dense Retrieval (DR) reaches state-of-the-art results in first-stage retrieval, but little is known about the mechanisms that contribute to its success. Therefore, in this work, we conduct an interpretation study of recently proposed DR…

Information Retrieval · Computer Science 2021-11-30 Jingtao Zhan , Jiaxin Mao , Yiqun Liu , Jiafeng Guo , Min Zhang , Shaoping Ma

Contrastive learning has been the dominant approach to training dense retrieval models. In this work, we investigate the impact of ranking context - an often overlooked aspect of learning dense retrieval models. In particular, we examine…

Information Retrieval · Computer Science 2023-10-24 George Zerveas , Navid Rekabsaz , Daniel Cohen , Carsten Eickhoff

Information retrieval (IR) is essential in search engines and dialogue systems as well as natural language processing tasks such as open-domain question answering. IR serve an important function in the biomedical domain, where content and…

Information Retrieval · Computer Science 2022-01-20 Man Luo , Arindam Mitra , Tejas Gokhale , Chitta Baral

Incorporating external knowledge bases in traditional retrieval-augmented generation (RAG) relies on parsing the document, followed by querying a language model with the parsed information via in-context learning. While effective for…

Computation and Language · Computer Science 2026-02-03 Jacob Si , Mike Qu , Michelle Lee , Marek Rei , Yingzhen Li

Prior work on English monolingual retrieval has shown that a cross-encoder trained using a large number of relevance judgments for query-document pairs can be used as a teacher to train more efficient, but similarly effective, dual-encoder…

Information Retrieval · Computer Science 2024-01-11 Eugene Yang , Dawn Lawrie , James Mayfield , Douglas W. Oard , Scott Miller

Despite the advantages of their low-resource settings, traditional sparse retrievers depend on exact matching approaches between high-dimensional bag-of-words (BoW) representations of both the queries and the collection. As a result,…

Information Retrieval · Computer Science 2024-04-16 Dahlia Shehata

In dense retrieval, effective training hinges on selecting high quality hard negatives while avoiding false negatives. Recent methods apply heuristics based on positive document scores to identify hard negatives, improving both performance…

Information Retrieval · Computer Science 2025-08-19 Bongsu Kim