@inproceedings{zhao-etal-2025-beyond,
title = "Beyond Benchmarks: Building a Richer Cross-Document Event Coreference Dataset with Decontextualization",
author = "Zhao, Jin and
Tu, Jingxuan and
Ye, Bingyang and
Hu, Xinrui and
Xue, Nianwen and
Pustejovsky, James",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.178/",
doi = "10.18653/v1/2025.naacl-long.178",
pages = "3499--3513",
ISBN = "979-8-89176-189-6",
abstract = "Cross-Document Event Coreference (CDEC) annotation is challenging and difficult to scale, resulting in existing datasets being small and lacking diversity. We introduce a new approach leveraging large language models (LLMs) to decontextualize event mentions, by simplifying the document-level annotation task to sentence pairs with enriched context, enabling the creation of Richer EventCorefBank (RECB), a denser and more expressive dataset annotated at faster speed. Decontextualization has been shown to improve annotation speed without compromising quality and to enhance model performance. Our baseline experiment indicates that systems trained on RECB achieve comparable results on the EventCorefBank(ECB+) test set, showing the high quality of our dataset and its generalizability on other CDEC datasets. In addition, our evaluation shows that the strong baseline models are still struggling with RECB comparing to other CDEC datasets, suggesting that the richness and diversity of RECB present significant challenges to current CDEC systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2025-beyond">
<titleInfo>
<title>Beyond Benchmarks: Building a Richer Cross-Document Event Coreference Dataset with Decontextualization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingxuan</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bingyang</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinrui</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>Cross-Document Event Coreference (CDEC) annotation is challenging and difficult to scale, resulting in existing datasets being small and lacking diversity. We introduce a new approach leveraging large language models (LLMs) to decontextualize event mentions, by simplifying the document-level annotation task to sentence pairs with enriched context, enabling the creation of Richer EventCorefBank (RECB), a denser and more expressive dataset annotated at faster speed. Decontextualization has been shown to improve annotation speed without compromising quality and to enhance model performance. Our baseline experiment indicates that systems trained on RECB achieve comparable results on the EventCorefBank(ECB+) test set, showing the high quality of our dataset and its generalizability on other CDEC datasets. In addition, our evaluation shows that the strong baseline models are still struggling with RECB comparing to other CDEC datasets, suggesting that the richness and diversity of RECB present significant challenges to current CDEC systems.</abstract>
<identifier type="citekey">zhao-etal-2025-beyond</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.178</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.178/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>3499</start>
<end>3513</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Benchmarks: Building a Richer Cross-Document Event Coreference Dataset with Decontextualization
%A Zhao, Jin
%A Tu, Jingxuan
%A Ye, Bingyang
%A Hu, Xinrui
%A Xue, Nianwen
%A Pustejovsky, James
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F zhao-etal-2025-beyond
%X Cross-Document Event Coreference (CDEC) annotation is challenging and difficult to scale, resulting in existing datasets being small and lacking diversity. We introduce a new approach leveraging large language models (LLMs) to decontextualize event mentions, by simplifying the document-level annotation task to sentence pairs with enriched context, enabling the creation of Richer EventCorefBank (RECB), a denser and more expressive dataset annotated at faster speed. Decontextualization has been shown to improve annotation speed without compromising quality and to enhance model performance. Our baseline experiment indicates that systems trained on RECB achieve comparable results on the EventCorefBank(ECB+) test set, showing the high quality of our dataset and its generalizability on other CDEC datasets. In addition, our evaluation shows that the strong baseline models are still struggling with RECB comparing to other CDEC datasets, suggesting that the richness and diversity of RECB present significant challenges to current CDEC systems.
%R 10.18653/v1/2025.naacl-long.178
%U https://aclanthology.org/2025.naacl-long.178/
%U https://doi.org/10.18653/v1/2025.naacl-long.178
%P 3499-3513
Markdown (Informal)
[Beyond Benchmarks: Building a Richer Cross-Document Event Coreference Dataset with Decontextualization](https://aclanthology.org/2025.naacl-long.178/) (Zhao et al., NAACL 2025)
ACL