English
Related papers

Related papers: ExStrucTiny: A Benchmark for Schema-Variable Struc…

200 papers

Typically, information extraction (IE) requires a pipeline approach: first, a sequence labeling model is trained on manually annotated documents to extract relevant spans; then, when a new document arrives, a model predicts spans which are…

Computation and Language · Computer Science 2021-10-12 Benjamin Townsend , Eamon Ito-Fisher , Lily Zhang , Madison May

Advances in Visually Rich Document Understanding (VrDU) have enabled information extraction and question answering over documents with complex layouts. Two tropes of architectures have emerged -- transformer-based models inspired by LLMs,…

Computation and Language · Computer Science 2024-01-08 Dongsheng Wang , Zhiqiang Ma , Armineh Nourbakhsh , Kang Gu , Sameena Shah

Document-level relation extraction (DocRE) models generally use graph networks to implicitly model the reasoning skill (i.e., pattern recognition, logical reasoning, coreference reasoning, etc.) related to the relation between one entity…

Computation and Language · Computer Science 2021-06-04 Wang Xu , Kehai Chen , Tiejun Zhao

This paper proposes a structure-aware decoding method based on large language models to address the difficulty of traditional approaches in maintaining both semantic integrity and structural consistency in nested and overlapping entity…

Computation and Language · Computer Science 2026-01-29 Zhimin Qiu , Di Wu , Feng Liu , Yuxiao Wang

We propose a new paradigm for universal information extraction (IE) that is compatible with any schema format and applicable to a list of IE tasks, such as named entity recognition, relation extraction, event extraction and sentiment…

Computation and Language · Computer Science 2023-05-23 Ping Yang , Junyu Lu , Ruyi Gan , Junjie Wang , Yuxiang Zhang , Jiaxing Zhang , Pingjian Zhang

Information extraction (IE) plays very important role in natural language processing (NLP) and is fundamental to many NLP applications that used to extract structured information from unstructured text data. Heuristic-based searching and…

Computation and Language · Computer Science 2023-07-04 Shiyu Yuan , Carlo Lipizzi

Manual chart review remains an extremely time-consuming and resource-intensive component of clinical research, requiring experts to extract often complex information from unstructured electronic health record (EHR) narratives. We present a…

Understanding vehicles in images is important for various applications such as intelligent transportation and self-driving system. Existing vehicle-centric works typically pre-train models on large-scale classification datasets and then…

Computer Vision and Pattern Recognition · Computer Science 2023-12-18 Xiao Wang , Wentao Wu , Chenglong Li , Zhicheng Zhao , Zhe Chen , Yukai Shi , Jin Tang

Structural extraction of events within discourse is critical since it avails a deeper understanding of communication patterns and behavior trends. Event argument extraction (EAE), at the core of event-centric understanding, is the task of…

Computation and Language · Computer Science 2025-03-21 Xinliang Frederick Zhang , Carter Blum , Temma Choji , Shalin Shah , Alakananda Vempala

Legal practitioners often face a vast amount of documents. Lawyers, for instance, search for appropriate precedents favorable to their clients, while the number of legal precedents is ever-growing. Although legal search engines can assist…

Computation and Language · Computer Science 2022-11-04 Wonseok Hwang , Saehee Eom , Hanuhl Lee , Hai Jin Park , Minjoon Seo

Many business documents processed in modern NLP and IR pipelines are visually rich: in addition to text, their semantics can also be captured by visual traits such as layout, format, and fonts. We study the problem of information extraction…

Computation and Language · Computer Science 2020-05-25 Mengxi Wei , Yifan He , Qiong Zhang

Industrial standards and normative documents exhibit intricate hierarchical structures, domain-specific lexicons, and extensive cross-referential dependencies, which making it challenging to process them directly by Large Language Models…

Information Retrieval · Computer Science 2026-04-14 Aiman Al Masoud , Marco Arazzi , Simone Germani , Antonino Nocera

Relation extraction (RE) is a sub-discipline of information extraction (IE) which focuses on the prediction of a relational predicate from a natural-language input unit (such as a sentence, a clause, or even a short paragraph consisting of…

Computation and Language · Computer Science 2022-12-20 Alessandro Temperoni , Maria Biryukov , Martin Theobald

Business Document Information Extraction (BDIE) is the problem of transforming a blob of unstructured information (raw text, scanned documents, etc.) into a structured format that downstream systems can parse and use. It has two main tasks:…

Computation and Language · Computer Science 2024-05-31 Franz Louis Cesista , Rui Aguiar , Jason Kim , Paolo Acilo

Biomedical evidence synthesis relies on accurate extraction of methodological, laboratory, and outcome variables from full-text research articles, yet these variables are embedded in complex scientific PDFs that make manual abstraction…

Computation and Language · Computer Science 2026-01-22 Pouria Mortezaagha , Joseph Shaw , Bowen Sun , Arya Rahgozar

Document-level information extraction (IE) is a crucial task in natural language processing (NLP). This paper conducts a systematic review of recent document-level IE literature. In addition, we conduct a thorough error analysis with…

Computation and Language · Computer Science 2023-09-26 Hanwen Zheng , Sijia Wang , Lifu Huang

Relation extraction (RE) has recently moved from the sentence-level to document-level, which requires aggregating document information and using entities and mentions for reasoning. Existing works put entity nodes and mention nodes with…

Computation and Language · Computer Science 2023-03-08 Hongfei Liu , Zhao Kang , Lizong Zhang , Ling Tian , Fujun Hua

Information extraction from copy-heavy documents, characterized by massive volumes of structurally similar content, represents a critical yet understudied challenge in enterprise document processing. We present a systematic framework that…

Computation and Language · Computer Science 2025-10-14 Zilong Wang , Xiaoyu Shen

Compared to the general news domain, information extraction (IE) from biomedical text requires much broader domain knowledge. However, many previous IE methods do not utilize any external knowledge during inference. Due to the exponential…

Computation and Language · Computer Science 2021-06-02 Tuan Lai , Heng Ji , ChengXiang Zhai , Quan Hung Tran

Document-based Question-Answering (QA) tasks are crucial for precise information retrieval. While some existing work focus on evaluating large language models performance on retrieving and answering questions from documents, assessing the…