English
Related papers

Related papers: BOOKCOREF: Coreference Resolution at Book Scale

200 papers

We consider the task of document-level entity linking (EL), where it is important to make consistent decisions for entity mentions over the full document jointly. We aim to leverage explicit "connections" among mentions within the document…

Computation and Language · Computer Science 2022-07-05 Klim Zaporojets , Johannes Deleu , Yiwei Jiang , Thomas Demeester , Chris Develder

While large language models now handle million-token contexts, their capacity for reasoning across entire document repositories remains largely untested. Existing benchmarks are inadequate, as they are mostly limited to single long texts or…

Computation and Language · Computer Science 2026-04-28 Zhiyuan Lu , Chenliang Li , Yingcheng Shi , Weizhou Shen , Ming Yan , Fei Huang

Coreference Resolution (CR) is a critical task in Natural Language Processing (NLP). Current research faces a key dilemma: whether to further explore the potential of supervised neural methods based on small language models, whose…

Computation and Language · Computer Science 2026-05-08 Kangyang Luo , Yuzhuo Bai , Shuzheng Si , Cheng Gao , Zhitong Wang , Yingli Shen , Wenhao Li , Zhu Liu , Yufeng Han , Jiayi Wu , Cunliang Kong , Maosong Sun

Recent evaluation protocols for Cross-document (CD) coreference resolution have often been inconsistent or lenient, leading to incomparable results across works and overestimation of performance. To facilitate proper future research on this…

Computation and Language · Computer Science 2020-10-26 Arie Cattan , Alon Eirew , Gabriel Stanovsky , Mandar Joshi , Ido Dagan

Coreference resolution involves the task of identifying text spans within a discourse that pertain to the same real-world entity. While this task has been extensively explored in the English language, there has been a notable scarcity of…

Computation and Language · Computer Science 2024-03-26 Ritwik Mishra , Pooja Desur , Rajiv Ratn Shah , Ponnurangam Kumaraguru

The emergence of long-context language models with context windows extending to millions of tokens has created new opportunities for sophisticated code understanding and software development evaluation. We propose LoCoBench, a comprehensive…

Document-level relation extraction is to extract relation facts from a document consisting of multiple sentences, in which pronoun crossed sentences are a ubiquitous phenomenon against a single sentence. However, most of the previous works…

Computation and Language · Computer Science 2022-02-23 Zhongxuan Xue , Rongzhen Li , Qizhu Dai , Zhong Jiang

Deep text understanding, which requires the connections between a given document and prior knowledge beyond its text, has been highlighted by many benchmarks in recent years. However, these benchmarks have encountered two major limitations.…

Computation and Language · Computer Science 2023-07-07 Zijun Yao , Yantao Liu , Xin Lv , Shulin Cao , Jifan Yu , Lei Hou , Juanzi Li

Coreference resolution is essential for natural language understanding and has been long studied in NLP. In recent years, as the format of Question Answering (QA) became a standard for machine reading comprehension (MRC), there have been…

Computation and Language · Computer Science 2021-06-10 Mingzhu Wu , Nafise Sadat Moosavi , Dan Roth , Iryna Gurevych

We propose a sentence-incremental neural coreference resolution system which incrementally builds clusters after marking mention boundaries in a shift-reduce method. The system is aimed at bridging two recent approaches at coreference…

Computation and Language · Computer Science 2023-05-29 Matt Grenander , Shay B. Cohen , Mark Steedman

In this paper, we present an accurate and extensible approach for the coreference resolution task. We formulate the problem as a span prediction task, like in machine reading comprehension (MRC): A query is generated for each candidate…

Computation and Language · Computer Science 2020-07-21 Wei Wu , Fei Wang , Arianna Yuan , Fei Wu , Jiwei Li

While coreference resolution typically involves various linguistic challenges, recent models are based on a single pairwise scorer for all types of pairs. We present LingMess, a new coreference model that defines different categories of…

Computation and Language · Computer Science 2023-02-13 Shon Otmazgin , Arie Cattan , Yoav Goldberg

We present in this work a new dataset of coreference annotations for works of literature in English, covering 29,103 mentions in 210,532 tokens from 100 works of fiction. This dataset differs from previous coreference datasets in containing…

Computation and Language · Computer Science 2020-05-18 David Bamman , Olivia Lewke , Anya Mansoor

Recent coreference resolution models rely heavily on span representations to find coreference links between word spans. As the number of spans is $O(n^2)$ in the length of text and the number of potential links is $O(n^4)$, various pruning…

Computation and Language · Computer Science 2022-04-12 Vladimir Dobrovolskii

Coreference resolution aims to identify in a text all mentions that refer to the same real-world entity. The state-of-the-art end-to-end neural coreference model considers all text spans in a document as potential mentions and learns to…

Computation and Language · Computer Science 2018-05-15 Rui Zhang , Cicero Nogueira dos Santos , Michihiro Yasunaga , Bing Xiang , Dragomir Radev

Recent work on extending coreference resolution across domains and languages relies on annotated data in both the target domain and language. At the same time, pre-trained large language models (LMs) have been reported to exhibit strong…

Computation and Language · Computer Science 2023-11-16 Nghia T. Le , Alan Ritter

The state-of-the-art models for coreference resolution are based on independent mention pair-wise decisions. We propose a modelling approach that learns coreference at the document-level and takes global decisions. For this purpose, we…

Computation and Language · Computer Science 2022-04-01 Lesly Miculicich , James Henderson

Current work on automatic coreference resolution has focused on the OntoNotes benchmark dataset, due to both its size and consistency. However many aspects of the OntoNotes annotation scheme are not well understood by NLP practitioners,…

Computation and Language · Computer Science 2021-12-21 Amir Zeldes

Recently, there has been a growing interest among large language model (LLM) developers in LLM-based document reading systems, which enable users to upload their own documents and pose questions related to the document contents, going…

Computation and Language · Computer Science 2024-07-16 Anni Zou , Wenhao Yu , Hongming Zhang , Kaixin Ma , Deng Cai , Zhuosheng Zhang , Hai Zhao , Dong Yu

We introduce PreCo, a large-scale English dataset for coreference resolution. The dataset is designed to embody the core challenges in coreference, such as entity representation, by alleviating the challenge of low overlap between training…

Computation and Language · Computer Science 2018-10-24 Hong Chen , Zhenhua Fan , Hao Lu , Alan L. Yuille , Shu Rong