<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lai-etal-2023-improving">
    <titleInfo>
        <title>Improving Prediction Backward-Compatiblility in NLP Model Upgrade with Gated Fusion</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yi-An</namePart>
        <namePart type="family">Lai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Elman</namePart>
        <namePart type="family">Mansimov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuqing</namePart>
        <namePart type="family">Xie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yi</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Andreas</namePart>
            <namePart type="family">Vlachos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Isabelle</namePart>
            <namePart type="family">Augenstein</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dubrovnik, Croatia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>When upgrading neural models to a newer version, new errors that were not encountered in the legacy version can be introduced, known as regression errors. This inconsistent behavior during model upgrade often outweighs the benefits of accuracy gain and hinders the adoption of new models. To mitigate regression errors from model upgrade, distillation and ensemble have proven to be viable solutions without significant compromise in performance. Despite the progress, these approaches attained an incremental reduction in regression which is still far from achieving backward-compatible model upgrade. In this work, we propose a novel method, Gated Fusion, that promotes backward compatibility via learning to mix predictions between old and new models. Empirical results on two distinct model upgrade scenarios show that our method reduces the number of regression errors by 62% on average, outperforming the strongest baseline by an average of 25%.</abstract>
    <identifier type="citekey">lai-etal-2023-improving</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-eacl.74</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-eacl.74</url>
    </location>
    <part>
        <date>2023-05</date>
        <extent unit="page">
            <start>1010</start>
            <end>1022</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Improving Prediction Backward-Compatiblility in NLP Model Upgrade with Gated Fusion
%A Lai, Yi-An
%A Mansimov, Elman
%A Xie, Yuqing
%A Zhang, Yi
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F lai-etal-2023-improving
%X When upgrading neural models to a newer version, new errors that were not encountered in the legacy version can be introduced, known as regression errors. This inconsistent behavior during model upgrade often outweighs the benefits of accuracy gain and hinders the adoption of new models. To mitigate regression errors from model upgrade, distillation and ensemble have proven to be viable solutions without significant compromise in performance. Despite the progress, these approaches attained an incremental reduction in regression which is still far from achieving backward-compatible model upgrade. In this work, we propose a novel method, Gated Fusion, that promotes backward compatibility via learning to mix predictions between old and new models. Empirical results on two distinct model upgrade scenarios show that our method reduces the number of regression errors by 62% on average, outperforming the strongest baseline by an average of 25%.
%R 10.18653/v1/2023.findings-eacl.74
%U https://aclanthology.org/2023.findings-eacl.74
%U https://doi.org/10.18653/v1/2023.findings-eacl.74
%P 1010-1022

Markdown (Informal)

[Improving Prediction Backward-Compatiblility in NLP Model Upgrade with Gated Fusion](https://aclanthology.org/2023.findings-eacl.74) (Lai et al., Findings 2023)

• Improving Prediction Backward-Compatiblility in NLP Model Upgrade with Gated Fusion (Lai et al., Findings 2023)

ACL

• Yi-An Lai, Elman Mansimov, Yuqing Xie, and Yi Zhang. 2023. Improving Prediction Backward-Compatiblility in NLP Model Upgrade with Gated Fusion. In Findings of the Association for Computational Linguistics: EACL 2023, pages 1010–1022, Dubrovnik, Croatia. Association for Computational Linguistics.