@inproceedings{zhang-etal-2023-seq2seq,
title = "Seq2seq is All You Need for Coreference Resolution",
author = "Zhang, Wenzheng and
Wiseman, Sam and
Stratos, Karl",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.704/",
doi = "10.18653/v1/2023.emnlp-main.704",
pages = "11493--11504",
abstract = "Existing works on coreference resolution suggest that task-specific models are necessary to achieve state-of-the-art performance. In this work, we present compelling evidence that such models are not necessary. We finetune a pretrained seq2seq transformer to map an input document to a tagged sequence encoding the coreference annotation. Despite the extreme simplicity, our model outperforms or closely matches the best coreference systems in the literature on an array of datasets. We consider an even simpler version of seq2seq that generates only the tagged spans and find it highly performant. Our analysis shows that the model size, the amount of supervision, and the choice of sequence representations are key factors in performance."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2023-seq2seq">
<titleInfo>
<title>Seq2seq is All You Need for Coreference Resolution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenzheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sam</namePart>
<namePart type="family">Wiseman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karl</namePart>
<namePart type="family">Stratos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing works on coreference resolution suggest that task-specific models are necessary to achieve state-of-the-art performance. In this work, we present compelling evidence that such models are not necessary. We finetune a pretrained seq2seq transformer to map an input document to a tagged sequence encoding the coreference annotation. Despite the extreme simplicity, our model outperforms or closely matches the best coreference systems in the literature on an array of datasets. We consider an even simpler version of seq2seq that generates only the tagged spans and find it highly performant. Our analysis shows that the model size, the amount of supervision, and the choice of sequence representations are key factors in performance.</abstract>
<identifier type="citekey">zhang-etal-2023-seq2seq</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.704</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.704/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>11493</start>
<end>11504</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Seq2seq is All You Need for Coreference Resolution
%A Zhang, Wenzheng
%A Wiseman, Sam
%A Stratos, Karl
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zhang-etal-2023-seq2seq
%X Existing works on coreference resolution suggest that task-specific models are necessary to achieve state-of-the-art performance. In this work, we present compelling evidence that such models are not necessary. We finetune a pretrained seq2seq transformer to map an input document to a tagged sequence encoding the coreference annotation. Despite the extreme simplicity, our model outperforms or closely matches the best coreference systems in the literature on an array of datasets. We consider an even simpler version of seq2seq that generates only the tagged spans and find it highly performant. Our analysis shows that the model size, the amount of supervision, and the choice of sequence representations are key factors in performance.
%R 10.18653/v1/2023.emnlp-main.704
%U https://aclanthology.org/2023.emnlp-main.704/
%U https://doi.org/10.18653/v1/2023.emnlp-main.704
%P 11493-11504
Markdown (Informal)
[Seq2seq is All You Need for Coreference Resolution](https://aclanthology.org/2023.emnlp-main.704/) (Zhang et al., EMNLP 2023)
ACL
- Wenzheng Zhang, Sam Wiseman, and Karl Stratos. 2023. Seq2seq is All You Need for Coreference Resolution. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 11493–11504, Singapore. Association for Computational Linguistics.