@inproceedings{zhao-etal-2022-pcr4all,
title = "{PCR}4{ALL}: A Comprehensive Evaluation Benchmark for Pronoun Coreference Resolution in {E}nglish",
author = "Zhao, Xinran and
Zhang, Hongming and
Song, Yangqiu",
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-1.641",
pages = "5963--5973",
abstract = "Pronoun Coreference Resolution (PCR) is the task of resolving pronominal expressions to all mentions they refer to. The correct resolution of pronouns typically involves the complex inference over both linguistic knowledge and general world knowledge. Recently, with the help of pre-trained language representation models, the community has made significant progress on various PCR tasks. However, as most existing works focus on developing PCR models for specific datasets and measuring the accuracy or F1 alone, it is still unclear whether current PCR systems are reliable in real applications. Motivated by this, we propose PCR4ALL, a new benchmark and a toolbox that evaluates and analyzes the performance of PCR systems from different perspectives (i.e., knowledge source, domain, data size, frequency, relevance, and polarity). Experiments demonstrate notable performance differences when the models are examined from different angles. We hope that PCR4ALL can motivate the community to pay more attention to solving the overall PCR problem and understand the performance comprehensively. All data and codes are available at: \url{https://github.com/HKUST-KnowComp/PCR4ALL}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2022-pcr4all">
<titleInfo>
<title>PCR4ALL: A Comprehensive Evaluation Benchmark for Pronoun Coreference Resolution in English</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinran</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongming</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yangqiu</namePart>
<namePart type="family">Song</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>Pronoun Coreference Resolution (PCR) is the task of resolving pronominal expressions to all mentions they refer to. The correct resolution of pronouns typically involves the complex inference over both linguistic knowledge and general world knowledge. Recently, with the help of pre-trained language representation models, the community has made significant progress on various PCR tasks. However, as most existing works focus on developing PCR models for specific datasets and measuring the accuracy or F1 alone, it is still unclear whether current PCR systems are reliable in real applications. Motivated by this, we propose PCR4ALL, a new benchmark and a toolbox that evaluates and analyzes the performance of PCR systems from different perspectives (i.e., knowledge source, domain, data size, frequency, relevance, and polarity). Experiments demonstrate notable performance differences when the models are examined from different angles. We hope that PCR4ALL can motivate the community to pay more attention to solving the overall PCR problem and understand the performance comprehensively. All data and codes are available at: https://github.com/HKUST-KnowComp/PCR4ALL.</abstract>
<identifier type="citekey">zhao-etal-2022-pcr4all</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.641</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5963</start>
<end>5973</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PCR4ALL: A Comprehensive Evaluation Benchmark for Pronoun Coreference Resolution in English
%A Zhao, Xinran
%A Zhang, Hongming
%A Song, Yangqiu
%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 zhao-etal-2022-pcr4all
%X Pronoun Coreference Resolution (PCR) is the task of resolving pronominal expressions to all mentions they refer to. The correct resolution of pronouns typically involves the complex inference over both linguistic knowledge and general world knowledge. Recently, with the help of pre-trained language representation models, the community has made significant progress on various PCR tasks. However, as most existing works focus on developing PCR models for specific datasets and measuring the accuracy or F1 alone, it is still unclear whether current PCR systems are reliable in real applications. Motivated by this, we propose PCR4ALL, a new benchmark and a toolbox that evaluates and analyzes the performance of PCR systems from different perspectives (i.e., knowledge source, domain, data size, frequency, relevance, and polarity). Experiments demonstrate notable performance differences when the models are examined from different angles. We hope that PCR4ALL can motivate the community to pay more attention to solving the overall PCR problem and understand the performance comprehensively. All data and codes are available at: https://github.com/HKUST-KnowComp/PCR4ALL.
%U https://aclanthology.org/2022.lrec-1.641
%P 5963-5973
Markdown (Informal)
[PCR4ALL: A Comprehensive Evaluation Benchmark for Pronoun Coreference Resolution in English](https://aclanthology.org/2022.lrec-1.641) (Zhao et al., LREC 2022)
ACL