@inproceedings{eirew-etal-2021-wec,
title = "{WEC}: Deriving a Large-scale Cross-document Event Coreference dataset from {W}ikipedia",
author = "Eirew, Alon and
Cattan, Arie and
Dagan, Ido",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.198",
doi = "10.18653/v1/2021.naacl-main.198",
pages = "2498--2510",
abstract = "Cross-document event coreference resolution is a foundational task for NLP applications involving multi-text processing. However, existing corpora for this task are scarce and relatively small, while annotating only modest-size clusters of documents belonging to the same topic. To complement these resources and enhance future research, we present Wikipedia Event Coreference (WEC), an efficient methodology for gathering a large-scale dataset for cross-document event coreference from Wikipedia, where coreference links are not restricted within predefined topics. We apply this methodology to the English Wikipedia and extract our large-scale WEC-Eng dataset. Notably, our dataset creation method is generic and can be applied with relatively little effort to other Wikipedia languages. To set baseline results, we develop an algorithm that adapts components of state-of-the-art models for within-document coreference resolution to the cross-document setting. Our model is suitably efficient and outperforms previously published state-of-the-art results for the task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eirew-etal-2021-wec">
<titleInfo>
<title>WEC: Deriving a Large-scale Cross-document Event Coreference dataset from Wikipedia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alon</namePart>
<namePart type="family">Eirew</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arie</namePart>
<namePart type="family">Cattan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ido</namePart>
<namePart type="family">Dagan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Cross-document event coreference resolution is a foundational task for NLP applications involving multi-text processing. However, existing corpora for this task are scarce and relatively small, while annotating only modest-size clusters of documents belonging to the same topic. To complement these resources and enhance future research, we present Wikipedia Event Coreference (WEC), an efficient methodology for gathering a large-scale dataset for cross-document event coreference from Wikipedia, where coreference links are not restricted within predefined topics. We apply this methodology to the English Wikipedia and extract our large-scale WEC-Eng dataset. Notably, our dataset creation method is generic and can be applied with relatively little effort to other Wikipedia languages. To set baseline results, we develop an algorithm that adapts components of state-of-the-art models for within-document coreference resolution to the cross-document setting. Our model is suitably efficient and outperforms previously published state-of-the-art results for the task.</abstract>
<identifier type="citekey">eirew-etal-2021-wec</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.198</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.198</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>2498</start>
<end>2510</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WEC: Deriving a Large-scale Cross-document Event Coreference dataset from Wikipedia
%A Eirew, Alon
%A Cattan, Arie
%A Dagan, Ido
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F eirew-etal-2021-wec
%X Cross-document event coreference resolution is a foundational task for NLP applications involving multi-text processing. However, existing corpora for this task are scarce and relatively small, while annotating only modest-size clusters of documents belonging to the same topic. To complement these resources and enhance future research, we present Wikipedia Event Coreference (WEC), an efficient methodology for gathering a large-scale dataset for cross-document event coreference from Wikipedia, where coreference links are not restricted within predefined topics. We apply this methodology to the English Wikipedia and extract our large-scale WEC-Eng dataset. Notably, our dataset creation method is generic and can be applied with relatively little effort to other Wikipedia languages. To set baseline results, we develop an algorithm that adapts components of state-of-the-art models for within-document coreference resolution to the cross-document setting. Our model is suitably efficient and outperforms previously published state-of-the-art results for the task.
%R 10.18653/v1/2021.naacl-main.198
%U https://aclanthology.org/2021.naacl-main.198
%U https://doi.org/10.18653/v1/2021.naacl-main.198
%P 2498-2510
Markdown (Informal)
[WEC: Deriving a Large-scale Cross-document Event Coreference dataset from Wikipedia](https://aclanthology.org/2021.naacl-main.198) (Eirew et al., NAACL 2021)
ACL