@inproceedings{poot-van-cranenburgh-2020-benchmark,
title = "A Benchmark of Rule-Based and Neural Coreference Resolution in {D}utch Novels and News",
author = "Poot, Corb{\`e}n and
van Cranenburgh, Andreas",
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-1.9",
pages = "79--90",
abstract = "We evaluate a rule-based (Lee et al., 2013) and neural (Lee et al., 2018) coreference system on Dutch datasets of two domains: literary novels and news/Wikipedia text. The results provide insight into the relative strengths of data-driven and knowledge-driven systems, as well as the influence of domain, document length, and annotation schemes. The neural system performs best on news/Wikipedia text, while the rule-based system performs best on literature. The neural system shows weaknesses with limited training data and long documents, while the rule-based system is affected by annotation differences. The code and models used in this paper are available at https://github.com/andreasvc/crac2020",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="poot-van-cranenburgh-2020-benchmark">
<titleInfo>
<title>A Benchmark of Rule-Based and Neural Coreference Resolution in Dutch Novels and News</title>
</titleInfo>
<name type="personal">
<namePart type="given">Corbèn</namePart>
<namePart type="family">Poot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">van Cranenburgh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-dec</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>
<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>We evaluate a rule-based (Lee et al., 2013) and neural (Lee et al., 2018) coreference system on Dutch datasets of two domains: literary novels and news/Wikipedia text. The results provide insight into the relative strengths of data-driven and knowledge-driven systems, as well as the influence of domain, document length, and annotation schemes. The neural system performs best on news/Wikipedia text, while the rule-based system performs best on literature. The neural system shows weaknesses with limited training data and long documents, while the rule-based system is affected by annotation differences. The code and models used in this paper are available at https://github.com/andreasvc/crac2020</abstract>
<identifier type="citekey">poot-van-cranenburgh-2020-benchmark</identifier>
<location>
<url>https://aclanthology.org/2020.crac-1.9</url>
</location>
<part>
<date>2020-dec</date>
<extent unit="page">
<start>79</start>
<end>90</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Benchmark of Rule-Based and Neural Coreference Resolution in Dutch Novels and News
%A Poot, Corbèn
%A van Cranenburgh, Andreas
%S Proceedings of the Third Workshop on Computational Models of Reference, Anaphora and Coreference
%D 2020
%8 dec
%I Association for Computational Linguistics
%C Barcelona, Spain (online)
%F poot-van-cranenburgh-2020-benchmark
%X We evaluate a rule-based (Lee et al., 2013) and neural (Lee et al., 2018) coreference system on Dutch datasets of two domains: literary novels and news/Wikipedia text. The results provide insight into the relative strengths of data-driven and knowledge-driven systems, as well as the influence of domain, document length, and annotation schemes. The neural system performs best on news/Wikipedia text, while the rule-based system performs best on literature. The neural system shows weaknesses with limited training data and long documents, while the rule-based system is affected by annotation differences. The code and models used in this paper are available at https://github.com/andreasvc/crac2020
%U https://aclanthology.org/2020.crac-1.9
%P 79-90
Markdown (Informal)
[A Benchmark of Rule-Based and Neural Coreference Resolution in Dutch Novels and News](https://aclanthology.org/2020.crac-1.9) (Poot & van Cranenburgh, CRAC 2020)
ACL