<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="skachkova-etal-2023-multilingual">
    <titleInfo>
        <title>Multilingual coreference resolution: Adapt and Generate</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Natalia</namePart>
        <namePart type="family">Skachkova</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tatiana</namePart>
        <namePart type="family">Anikina</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anna</namePart>
        <namePart type="family">Mokhova</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 CRAC 2023 Shared Task on Multilingual Coreference Resolution</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Zdeněk</namePart>
            <namePart type="family">Žabokrtský</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Maciej</namePart>
            <namePart type="family">Ogrodniczuk</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>The paper presents two multilingual coreference resolution systems submitted for the CRAC Shared Task 2023. The DFKI-Adapt system achieves 61.86 F1 score on the shared task test data, outperforming the official baseline by 4.9 F1 points. This system uses a combination of different features and training settings, including character embeddings, adapter modules, joint pre-training and loss-based re-training. We provide evaluation for each of the settings on 12 different datasets and compare the results. The other submission DFKI-MPrompt uses a novel approach that involves prompting for mention generation. Although the scores achieved by this model are lower compared to the baseline, the method shows a new way of approaching the coreference task and provides good results with just five epochs of training.</abstract>
    <identifier type="citekey">skachkova-etal-2023-multilingual</identifier>
    <identifier type="doi">10.18653/v1/2023.crac-sharedtask.2</identifier>
    <location>
        <url>https://aclanthology.org/2023.crac-sharedtask.2</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>19</start>
            <end>33</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multilingual coreference resolution: Adapt and Generate
%A Skachkova, Natalia
%A Anikina, Tatiana
%A Mokhova, Anna
%Y Žabokrtský, Zdeněk
%Y Ogrodniczuk, Maciej
%S Proceedings of the CRAC 2023 Shared Task on Multilingual Coreference Resolution
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F skachkova-etal-2023-multilingual
%X The paper presents two multilingual coreference resolution systems submitted for the CRAC Shared Task 2023. The DFKI-Adapt system achieves 61.86 F1 score on the shared task test data, outperforming the official baseline by 4.9 F1 points. This system uses a combination of different features and training settings, including character embeddings, adapter modules, joint pre-training and loss-based re-training. We provide evaluation for each of the settings on 12 different datasets and compare the results. The other submission DFKI-MPrompt uses a novel approach that involves prompting for mention generation. Although the scores achieved by this model are lower compared to the baseline, the method shows a new way of approaching the coreference task and provides good results with just five epochs of training.
%R 10.18653/v1/2023.crac-sharedtask.2
%U https://aclanthology.org/2023.crac-sharedtask.2
%U https://doi.org/10.18653/v1/2023.crac-sharedtask.2
%P 19-33

Markdown (Informal)

[Multilingual coreference resolution: Adapt and Generate](https://aclanthology.org/2023.crac-sharedtask.2) (Skachkova et al., CRAC-WS 2023)

• Multilingual coreference resolution: Adapt and Generate (Skachkova et al., CRAC-WS 2023)

ACL

• Natalia Skachkova, Tatiana Anikina, and Anna Mokhova. 2023. Multilingual coreference resolution: Adapt and Generate. In Proceedings of the CRAC 2023 Shared Task on Multilingual Coreference Resolution, pages 19–33, Singapore. Association for Computational Linguistics.