@inproceedings{abzaliev-2019-gap,
title = "On {GAP} Coreference Resolution Shared Task: Insights from the 3rd Place Solution",
author = "Abzaliev, Artem",
editor = "Costa-juss{\`a}, Marta R. and
Hardmeier, Christian and
Radford, Will and
Webster, Kellie",
booktitle = "Proceedings of the First Workshop on Gender Bias in Natural Language Processing",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-3816",
doi = "10.18653/v1/W19-3816",
pages = "107--112",
abstract = "This paper presents the 3rd-place-winning solution to the GAP coreference resolution shared task. The approach adopted consists of two key components: fine-tuning the BERT language representation model (Devlin et al., 2018) and the usage of external datasets during the training process. The model uses hidden states from the intermediate BERT layers instead of the last layer. The resulting system almost eliminates the difference in log loss per gender during the cross-validation, while providing high performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abzaliev-2019-gap">
<titleInfo>
<title>On GAP Coreference Resolution Shared Task: Insights from the 3rd Place Solution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Abzaliev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Gender Bias in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</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">Will</namePart>
<namePart type="family">Radford</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kellie</namePart>
<namePart type="family">Webster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the 3rd-place-winning solution to the GAP coreference resolution shared task. The approach adopted consists of two key components: fine-tuning the BERT language representation model (Devlin et al., 2018) and the usage of external datasets during the training process. The model uses hidden states from the intermediate BERT layers instead of the last layer. The resulting system almost eliminates the difference in log loss per gender during the cross-validation, while providing high performance.</abstract>
<identifier type="citekey">abzaliev-2019-gap</identifier>
<identifier type="doi">10.18653/v1/W19-3816</identifier>
<location>
<url>https://aclanthology.org/W19-3816</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>107</start>
<end>112</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On GAP Coreference Resolution Shared Task: Insights from the 3rd Place Solution
%A Abzaliev, Artem
%Y Costa-jussà, Marta R.
%Y Hardmeier, Christian
%Y Radford, Will
%Y Webster, Kellie
%S Proceedings of the First Workshop on Gender Bias in Natural Language Processing
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F abzaliev-2019-gap
%X This paper presents the 3rd-place-winning solution to the GAP coreference resolution shared task. The approach adopted consists of two key components: fine-tuning the BERT language representation model (Devlin et al., 2018) and the usage of external datasets during the training process. The model uses hidden states from the intermediate BERT layers instead of the last layer. The resulting system almost eliminates the difference in log loss per gender during the cross-validation, while providing high performance.
%R 10.18653/v1/W19-3816
%U https://aclanthology.org/W19-3816
%U https://doi.org/10.18653/v1/W19-3816
%P 107-112
Markdown (Informal)
[On GAP Coreference Resolution Shared Task: Insights from the 3rd Place Solution](https://aclanthology.org/W19-3816) (Abzaliev, GeBNLP 2019)
ACL