<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bohnet-etal-2023-coreference">
    <titleInfo>
        <title>Coreference Resolution through a seq2seq Transition-Based System</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bernd</namePart>
        <namePart type="family">Bohnet</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chris</namePart>
        <namePart type="family">Alberti</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Michael</namePart>
        <namePart type="family">Collins</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Most recent coreference resolution systems use search algorithms over possible spans to identify mentions and resolve coreference. We instead present a coreference resolution system that uses a text-to-text (seq2seq) paradigm to predict mentions and links jointly. We implement the coreference system as a transition system and use multilingual T5 as an underlying language model. We obtain state-of-the-art accuracy on the CoNLL-2012 datasets with 83.3 F1-score for English (a 2.3 higher F1-score than previous work [Dobrovolskii, 2021]) using only CoNLL data for training, 68.5 F1-score for Arabic (+4.1 higher than previous work), and 74.3 F1-score for Chinese (+5.3). In addition we use the SemEval-2010 data sets for experiments in the zero-shot setting, a few-shot setting, and supervised setting using all available training data. We obtain substantially higher zero-shot F1-scores for 3 out of 4 languages than previous approaches and significantly exceed previous supervised state-of-the-art results for all five tested languages. We provide the code and models as open source.1</abstract>
    <identifier type="citekey">bohnet-etal-2023-coreference</identifier>
    <identifier type="doi">10.1162/tacl_a_00543</identifier>
    <location>
        <url>https://aclanthology.org/2023.tacl-1.13</url>
    </location>
    <part>
        <date>2023</date>
        <detail type="volume"><number>11</number></detail>
        <extent unit="page">
            <start>212</start>
            <end>226</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Coreference Resolution through a seq2seq Transition-Based System
%A Bohnet, Bernd
%A Alberti, Chris
%A Collins, Michael
%J Transactions of the Association for Computational Linguistics
%D 2023
%V 11
%I MIT Press
%C Cambridge, MA
%F bohnet-etal-2023-coreference
%X Most recent coreference resolution systems use search algorithms over possible spans to identify mentions and resolve coreference. We instead present a coreference resolution system that uses a text-to-text (seq2seq) paradigm to predict mentions and links jointly. We implement the coreference system as a transition system and use multilingual T5 as an underlying language model. We obtain state-of-the-art accuracy on the CoNLL-2012 datasets with 83.3 F1-score for English (a 2.3 higher F1-score than previous work [Dobrovolskii, 2021]) using only CoNLL data for training, 68.5 F1-score for Arabic (+4.1 higher than previous work), and 74.3 F1-score for Chinese (+5.3). In addition we use the SemEval-2010 data sets for experiments in the zero-shot setting, a few-shot setting, and supervised setting using all available training data. We obtain substantially higher zero-shot F1-scores for 3 out of 4 languages than previous approaches and significantly exceed previous supervised state-of-the-art results for all five tested languages. We provide the code and models as open source.1
%R 10.1162/tacl_a_00543
%U https://aclanthology.org/2023.tacl-1.13
%U https://doi.org/10.1162/tacl_a_00543
%P 212-226

Markdown (Informal)

[Coreference Resolution through a seq2seq Transition-Based System](https://aclanthology.org/2023.tacl-1.13) (Bohnet et al., TACL 2023)

• Coreference Resolution through a seq2seq Transition-Based System (Bohnet et al., TACL 2023)

ACL

• Bernd Bohnet, Chris Alberti, and Michael Collins. 2023. Coreference Resolution through a seq2seq Transition-Based System. Transactions of the Association for Computational Linguistics, 11:212–226.