@inproceedings{chai-etal-2020-evaluation,
title = "Evaluation of Coreference Resolution Systems Under Adversarial Attacks",
author = "Chai, Haixia and
Zhao, Wei and
Eger, Steffen and
Strube, Michael",
editor = "Braud, Chlo{\'e} and
Hardmeier, Christian and
Li, Junyi Jessy and
Louis, Annie and
Strube, Michael",
booktitle = "Proceedings of the First Workshop on Computational Approaches to Discourse",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.codi-1.16",
doi = "10.18653/v1/2020.codi-1.16",
pages = "154--159",
abstract = "A substantial overlap of coreferent mentions in the CoNLL dataset magnifies the recent progress on coreference resolution. This is because the CoNLL benchmark fails to evaluate the ability of coreference resolvers that requires linking novel mentions unseen at train time. In this work, we create a new dataset based on CoNLL, which largely decreases mention overlaps in the entire dataset and exposes the limitations of published resolvers on two aspects{---}lexical inference ability and understanding of low-level orthographic noise. Our findings show (1) the requirements for embeddings, used in resolvers, and for coreference resolutions are, by design, in conflict and (2) adversarial approaches are sometimes not legitimate to mitigate the obstacles, as they may falsely introduce mention overlaps in adversarial training and test sets, thus giving an inflated impression for the improvements.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chai-etal-2020-evaluation">
<titleInfo>
<title>Evaluation of Coreference Resolution Systems Under Adversarial Attacks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haixia</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steffen</namePart>
<namePart type="family">Eger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Strube</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Computational Approaches to Discourse</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chloé</namePart>
<namePart type="family">Braud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hardmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annie</namePart>
<namePart type="family">Louis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Strube</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>A substantial overlap of coreferent mentions in the CoNLL dataset magnifies the recent progress on coreference resolution. This is because the CoNLL benchmark fails to evaluate the ability of coreference resolvers that requires linking novel mentions unseen at train time. In this work, we create a new dataset based on CoNLL, which largely decreases mention overlaps in the entire dataset and exposes the limitations of published resolvers on two aspects—lexical inference ability and understanding of low-level orthographic noise. Our findings show (1) the requirements for embeddings, used in resolvers, and for coreference resolutions are, by design, in conflict and (2) adversarial approaches are sometimes not legitimate to mitigate the obstacles, as they may falsely introduce mention overlaps in adversarial training and test sets, thus giving an inflated impression for the improvements.</abstract>
<identifier type="citekey">chai-etal-2020-evaluation</identifier>
<identifier type="doi">10.18653/v1/2020.codi-1.16</identifier>
<location>
<url>https://aclanthology.org/2020.codi-1.16</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>154</start>
<end>159</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluation of Coreference Resolution Systems Under Adversarial Attacks
%A Chai, Haixia
%A Zhao, Wei
%A Eger, Steffen
%A Strube, Michael
%Y Braud, Chloé
%Y Hardmeier, Christian
%Y Li, Junyi Jessy
%Y Louis, Annie
%Y Strube, Michael
%S Proceedings of the First Workshop on Computational Approaches to Discourse
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F chai-etal-2020-evaluation
%X A substantial overlap of coreferent mentions in the CoNLL dataset magnifies the recent progress on coreference resolution. This is because the CoNLL benchmark fails to evaluate the ability of coreference resolvers that requires linking novel mentions unseen at train time. In this work, we create a new dataset based on CoNLL, which largely decreases mention overlaps in the entire dataset and exposes the limitations of published resolvers on two aspects—lexical inference ability and understanding of low-level orthographic noise. Our findings show (1) the requirements for embeddings, used in resolvers, and for coreference resolutions are, by design, in conflict and (2) adversarial approaches are sometimes not legitimate to mitigate the obstacles, as they may falsely introduce mention overlaps in adversarial training and test sets, thus giving an inflated impression for the improvements.
%R 10.18653/v1/2020.codi-1.16
%U https://aclanthology.org/2020.codi-1.16
%U https://doi.org/10.18653/v1/2020.codi-1.16
%P 154-159
Markdown (Informal)
[Evaluation of Coreference Resolution Systems Under Adversarial Attacks](https://aclanthology.org/2020.codi-1.16) (Chai et al., CODI 2020)
ACL