<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xia-van-durme-2022-online">
    <titleInfo>
        <title>Online Neural Coreference Resolution with Rollback</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Patrick</namePart>
        <namePart type="family">Xia</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Benjamin</namePart>
        <namePart type="family">Van Durme</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifth 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">Anna</namePart>
            <namePart type="family">Nedoluzhko</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">Massimo</namePart>
            <namePart type="family">Poesio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Humans process natural language online, whether reading a document or participating in multiparty dialogue. Recent advances in neural coreference resolution have focused on offline approaches that assume the full communication history as input. This is neither realistic nor sufficient if we wish to support dialogue understanding in real-time. We benchmark two existing, offline, models and highlight their shortcomings in the online setting. We then modify these models to perform online inference and introduce rollback: a short-term mechanism to correct mistakes. We demonstrate across five English datasets the effectiveness of this approach against an offline and a naive online model in terms of latency, final document-level coreference F1, and average running F1.</abstract>
    <identifier type="citekey">xia-van-durme-2022-online</identifier>
    <location>
        <url>https://aclanthology.org/2022.crac-1.2/</url>
    </location>
    <part>
        <date>2022-10</date>
        <extent unit="page">
            <start>13</start>
            <end>21</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Online Neural Coreference Resolution with Rollback
%A Xia, Patrick
%A Van Durme, Benjamin
%Y Ogrodniczuk, Maciej
%Y Pradhan, Sameer
%Y Nedoluzhko, Anna
%Y Ng, Vincent
%Y Poesio, Massimo
%S Proceedings of the Fifth Workshop on Computational Models of Reference, Anaphora and Coreference
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F xia-van-durme-2022-online
%X Humans process natural language online, whether reading a document or participating in multiparty dialogue. Recent advances in neural coreference resolution have focused on offline approaches that assume the full communication history as input. This is neither realistic nor sufficient if we wish to support dialogue understanding in real-time. We benchmark two existing, offline, models and highlight their shortcomings in the online setting. We then modify these models to perform online inference and introduce rollback: a short-term mechanism to correct mistakes. We demonstrate across five English datasets the effectiveness of this approach against an offline and a naive online model in terms of latency, final document-level coreference F1, and average running F1.
%U https://aclanthology.org/2022.crac-1.2/
%P 13-21

Markdown (Informal)

[Online Neural Coreference Resolution with Rollback](https://aclanthology.org/2022.crac-1.2/) (Xia & Van Durme, CRAC 2022)

• Online Neural Coreference Resolution with Rollback (Xia & Van Durme, CRAC 2022)

ACL

• Patrick Xia and Benjamin Van Durme. 2022. Online Neural Coreference Resolution with Rollback. In Proceedings of the Fifth Workshop on Computational Models of Reference, Anaphora and Coreference, pages 13–21, Gyeongju, Republic of Korea. Association for Computational Linguistics.