@inproceedings{zhukova-etal-2022-towards,
title = "Towards Evaluation of Cross-document Coreference Resolution Models Using Datasets with Diverse Annotation Schemes",
author = "Zhukova, Anastasia and
Hamborg, Felix and
Gipp, Bela",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.522",
pages = "4884--4893",
abstract = "Established cross-document coreference resolution (CDCR) datasets contain event-centric coreference chains of events and entities with identity relations. These datasets establish strict definitions of the coreference relations across related tests but typically ignore anaphora with more vague context-dependent loose coreference relations. In this paper, we qualitatively and quantitatively compare the annotation schemes of ECB+, a CDCR dataset with identity coreference relations, and NewsWCL50, a CDCR dataset with a mix of loose context-dependent and strict coreference relations. We propose a phrasing diversity metric (PD) that encounters for the diversity of full phrases unlike the previously proposed metrics and allows to evaluate lexical diversity of the CDCR datasets in a higher precision. The analysis shows that coreference chains of NewsWCL50 are more lexically diverse than those of ECB+ but annotating of NewsWCL50 leads to the lower inter-coder reliability. We discuss the different tasks that both CDCR datasets create for the CDCR models, i.e., lexical disambiguation and lexical diversity. Finally, to ensure generalizability of the CDCR models, we propose a direction for CDCR evaluation that combines CDCR datasets with multiple annotation schemes that focus of various properties of the coreference chains.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhukova-etal-2022-towards">
<titleInfo>
<title>Towards Evaluation of Cross-document Coreference Resolution Models Using Datasets with Diverse Annotation Schemes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anastasia</namePart>
<namePart type="family">Zhukova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Hamborg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bela</namePart>
<namePart type="family">Gipp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Established cross-document coreference resolution (CDCR) datasets contain event-centric coreference chains of events and entities with identity relations. These datasets establish strict definitions of the coreference relations across related tests but typically ignore anaphora with more vague context-dependent loose coreference relations. In this paper, we qualitatively and quantitatively compare the annotation schemes of ECB+, a CDCR dataset with identity coreference relations, and NewsWCL50, a CDCR dataset with a mix of loose context-dependent and strict coreference relations. We propose a phrasing diversity metric (PD) that encounters for the diversity of full phrases unlike the previously proposed metrics and allows to evaluate lexical diversity of the CDCR datasets in a higher precision. The analysis shows that coreference chains of NewsWCL50 are more lexically diverse than those of ECB+ but annotating of NewsWCL50 leads to the lower inter-coder reliability. We discuss the different tasks that both CDCR datasets create for the CDCR models, i.e., lexical disambiguation and lexical diversity. Finally, to ensure generalizability of the CDCR models, we propose a direction for CDCR evaluation that combines CDCR datasets with multiple annotation schemes that focus of various properties of the coreference chains.</abstract>
<identifier type="citekey">zhukova-etal-2022-towards</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.522</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>4884</start>
<end>4893</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Evaluation of Cross-document Coreference Resolution Models Using Datasets with Diverse Annotation Schemes
%A Zhukova, Anastasia
%A Hamborg, Felix
%A Gipp, Bela
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F zhukova-etal-2022-towards
%X Established cross-document coreference resolution (CDCR) datasets contain event-centric coreference chains of events and entities with identity relations. These datasets establish strict definitions of the coreference relations across related tests but typically ignore anaphora with more vague context-dependent loose coreference relations. In this paper, we qualitatively and quantitatively compare the annotation schemes of ECB+, a CDCR dataset with identity coreference relations, and NewsWCL50, a CDCR dataset with a mix of loose context-dependent and strict coreference relations. We propose a phrasing diversity metric (PD) that encounters for the diversity of full phrases unlike the previously proposed metrics and allows to evaluate lexical diversity of the CDCR datasets in a higher precision. The analysis shows that coreference chains of NewsWCL50 are more lexically diverse than those of ECB+ but annotating of NewsWCL50 leads to the lower inter-coder reliability. We discuss the different tasks that both CDCR datasets create for the CDCR models, i.e., lexical disambiguation and lexical diversity. Finally, to ensure generalizability of the CDCR models, we propose a direction for CDCR evaluation that combines CDCR datasets with multiple annotation schemes that focus of various properties of the coreference chains.
%U https://aclanthology.org/2022.lrec-1.522
%P 4884-4893
Markdown (Informal)
[Towards Evaluation of Cross-document Coreference Resolution Models Using Datasets with Diverse Annotation Schemes](https://aclanthology.org/2022.lrec-1.522) (Zhukova et al., LREC 2022)
ACL