@inproceedings{van-cranenburgh-etal-2021-hybrid,
title = "A Hybrid Rule-Based and Neural Coreference Resolution System with an Evaluation on {D}utch Literature",
author = {van Cranenburgh, Andreas and
Ploeger, Esther and
van den Berg, Frank and
Th{\"u}ss, Remi},
editor = "Ogrodniczuk, Maciej and
Pradhan, Sameer and
Poesio, Massimo and
Grishina, Yulia and
Ng, Vincent",
booktitle = "Proceedings of the Fourth Workshop on Computational Models of Reference, Anaphora and Coreference",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.crac-1.5",
doi = "10.18653/v1/2021.crac-1.5",
pages = "47--56",
abstract = "We introduce a modular, hybrid coreference resolution system that extends a rule-based baseline with three neural classifiers for the subtasks mention detection, mention attributes (gender, animacy, number), and pronoun resolution. The classifiers substantially increase coreference performance in our experiments with Dutch literature across all metrics on the development set: mention detection, LEA, CoNLL, and especially pronoun accuracy. However, on the test set, the best results are obtained with rule-based pronoun resolution. This inconsistent result highlights that the rule-based system is still a strong baseline, and more work is needed to improve pronoun resolution robustly for this dataset. While end-to-end neural systems require no feature engineering and achieve excellent performance in standard benchmarks with large training sets, our simple hybrid system scales well to long document coreference ({\textgreater}10k words) and attains superior results in our experiments on literature.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-cranenburgh-etal-2021-hybrid">
<titleInfo>
<title>A Hybrid Rule-Based and Neural Coreference Resolution System with an Evaluation on Dutch Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">van Cranenburgh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Esther</namePart>
<namePart type="family">Ploeger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frank</namePart>
<namePart type="family">van den Berg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Remi</namePart>
<namePart type="family">Thüss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth 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">Sameer</namePart>
<namePart type="family">Pradhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Massimo</namePart>
<namePart type="family">Poesio</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">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce a modular, hybrid coreference resolution system that extends a rule-based baseline with three neural classifiers for the subtasks mention detection, mention attributes (gender, animacy, number), and pronoun resolution. The classifiers substantially increase coreference performance in our experiments with Dutch literature across all metrics on the development set: mention detection, LEA, CoNLL, and especially pronoun accuracy. However, on the test set, the best results are obtained with rule-based pronoun resolution. This inconsistent result highlights that the rule-based system is still a strong baseline, and more work is needed to improve pronoun resolution robustly for this dataset. While end-to-end neural systems require no feature engineering and achieve excellent performance in standard benchmarks with large training sets, our simple hybrid system scales well to long document coreference (\textgreater10k words) and attains superior results in our experiments on literature.</abstract>
<identifier type="citekey">van-cranenburgh-etal-2021-hybrid</identifier>
<identifier type="doi">10.18653/v1/2021.crac-1.5</identifier>
<location>
<url>https://aclanthology.org/2021.crac-1.5</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>47</start>
<end>56</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Hybrid Rule-Based and Neural Coreference Resolution System with an Evaluation on Dutch Literature
%A van Cranenburgh, Andreas
%A Ploeger, Esther
%A van den Berg, Frank
%A Thüss, Remi
%Y Ogrodniczuk, Maciej
%Y Pradhan, Sameer
%Y Poesio, Massimo
%Y Grishina, Yulia
%Y Ng, Vincent
%S Proceedings of the Fourth Workshop on Computational Models of Reference, Anaphora and Coreference
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F van-cranenburgh-etal-2021-hybrid
%X We introduce a modular, hybrid coreference resolution system that extends a rule-based baseline with three neural classifiers for the subtasks mention detection, mention attributes (gender, animacy, number), and pronoun resolution. The classifiers substantially increase coreference performance in our experiments with Dutch literature across all metrics on the development set: mention detection, LEA, CoNLL, and especially pronoun accuracy. However, on the test set, the best results are obtained with rule-based pronoun resolution. This inconsistent result highlights that the rule-based system is still a strong baseline, and more work is needed to improve pronoun resolution robustly for this dataset. While end-to-end neural systems require no feature engineering and achieve excellent performance in standard benchmarks with large training sets, our simple hybrid system scales well to long document coreference (\textgreater10k words) and attains superior results in our experiments on literature.
%R 10.18653/v1/2021.crac-1.5
%U https://aclanthology.org/2021.crac-1.5
%U https://doi.org/10.18653/v1/2021.crac-1.5
%P 47-56
Markdown (Informal)
[A Hybrid Rule-Based and Neural Coreference Resolution System with an Evaluation on Dutch Literature](https://aclanthology.org/2021.crac-1.5) (van Cranenburgh et al., CRAC 2021)
ACL