@inproceedings{aloraini-etal-2020-neural,
title = "Neural Coreference Resolution for {A}rabic",
author = "Aloraini, Abdulrahman and
Yu, Juntao and
Poesio, Massimo",
editor = "Ogrodniczuk, Maciej and
Ng, Vincent and
Grishina, Yulia and
Pradhan, Sameer",
booktitle = "Proceedings of the Third Workshop on Computational Models of Reference, Anaphora and Coreference",
month = dec,
year = "2020",
address = "Barcelona, Spain (online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.crac-1.11/",
pages = "99--110",
abstract = {No neural coreference resolver for Arabic exists, in fact we are not aware of any learning-based coreference resolver for Arabic since (Bj{\"o}rkelund and Kuhn, 2014). In this paper, we introduce a coreference resolution system for Arabic based on Lee et al`s end-to-end architecture combined with the Arabic version of bert and an external mention detector. As far as we know, this is the first neural coreference resolution system aimed specifically to Arabic, and it substantially outperforms the existing state-of-the-art on OntoNotes 5.0 with a gain of 15.2 points conll F1. We also discuss the current limitations of the task for Arabic and possible approaches that can tackle these challenges.}
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aloraini-etal-2020-neural">
<titleInfo>
<title>Neural Coreference Resolution for Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdulrahman</namePart>
<namePart type="family">Aloraini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juntao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Massimo</namePart>
<namePart type="family">Poesio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Computational Models of Reference, Anaphora and Coreference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Ogrodniczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulia</namePart>
<namePart type="family">Grishina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sameer</namePart>
<namePart type="family">Pradhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>No neural coreference resolver for Arabic exists, in fact we are not aware of any learning-based coreference resolver for Arabic since (Björkelund and Kuhn, 2014). In this paper, we introduce a coreference resolution system for Arabic based on Lee et al‘s end-to-end architecture combined with the Arabic version of bert and an external mention detector. As far as we know, this is the first neural coreference resolution system aimed specifically to Arabic, and it substantially outperforms the existing state-of-the-art on OntoNotes 5.0 with a gain of 15.2 points conll F1. We also discuss the current limitations of the task for Arabic and possible approaches that can tackle these challenges.</abstract>
<identifier type="citekey">aloraini-etal-2020-neural</identifier>
<location>
<url>https://aclanthology.org/2020.crac-1.11/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>99</start>
<end>110</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Coreference Resolution for Arabic
%A Aloraini, Abdulrahman
%A Yu, Juntao
%A Poesio, Massimo
%Y Ogrodniczuk, Maciej
%Y Ng, Vincent
%Y Grishina, Yulia
%Y Pradhan, Sameer
%S Proceedings of the Third Workshop on Computational Models of Reference, Anaphora and Coreference
%D 2020
%8 December
%I Association for Computational Linguistics
%C Barcelona, Spain (online)
%F aloraini-etal-2020-neural
%X No neural coreference resolver for Arabic exists, in fact we are not aware of any learning-based coreference resolver for Arabic since (Björkelund and Kuhn, 2014). In this paper, we introduce a coreference resolution system for Arabic based on Lee et al‘s end-to-end architecture combined with the Arabic version of bert and an external mention detector. As far as we know, this is the first neural coreference resolution system aimed specifically to Arabic, and it substantially outperforms the existing state-of-the-art on OntoNotes 5.0 with a gain of 15.2 points conll F1. We also discuss the current limitations of the task for Arabic and possible approaches that can tackle these challenges.
%U https://aclanthology.org/2020.crac-1.11/
%P 99-110
Markdown (Informal)
[Neural Coreference Resolution for Arabic](https://aclanthology.org/2020.crac-1.11/) (Aloraini et al., CRAC 2020)
ACL
- Abdulrahman Aloraini, Juntao Yu, and Massimo Poesio. 2020. Neural Coreference Resolution for Arabic. In Proceedings of the Third Workshop on Computational Models of Reference, Anaphora and Coreference, pages 99–110, Barcelona, Spain (online). Association for Computational Linguistics.