<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2023-continual">
    <titleInfo>
        <title>Continual Knowledge Distillation for Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yuanchi</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Peng</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maosong</namePart>
        <namePart type="family">Sun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>While many parallel corpora are not publicly accessible for data copyright, data privacy and competitive differentiation reasons, trained translation models are increasingly available on open platforms. In this work, we propose a method called continual knowledge distillation to take advantage of existing translation models to improve one model of interest. The basic idea is to sequentially transfer knowledge from each trained model to the distilled model. Extensive experiments on Chinese-English and German-English datasets show that our method achieves significant and consistent improvements over strong baselines under both homogeneous and heterogeneous trained model settings and is robust to malicious models.</abstract>
    <identifier type="citekey">zhang-etal-2023-continual</identifier>
    <identifier type="doi">10.18653/v1/2023.acl-long.443</identifier>
    <location>
        <url>https://aclanthology.org/2023.acl-long.443</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>7978</start>
            <end>7996</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Continual Knowledge Distillation for Neural Machine Translation
%A Zhang, Yuanchi
%A Li, Peng
%A Sun, Maosong
%A Liu, Yang
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F zhang-etal-2023-continual
%X While many parallel corpora are not publicly accessible for data copyright, data privacy and competitive differentiation reasons, trained translation models are increasingly available on open platforms. In this work, we propose a method called continual knowledge distillation to take advantage of existing translation models to improve one model of interest. The basic idea is to sequentially transfer knowledge from each trained model to the distilled model. Extensive experiments on Chinese-English and German-English datasets show that our method achieves significant and consistent improvements over strong baselines under both homogeneous and heterogeneous trained model settings and is robust to malicious models.
%R 10.18653/v1/2023.acl-long.443
%U https://aclanthology.org/2023.acl-long.443
%U https://doi.org/10.18653/v1/2023.acl-long.443
%P 7978-7996

Markdown (Informal)

[Continual Knowledge Distillation for Neural Machine Translation](https://aclanthology.org/2023.acl-long.443) (Zhang et al., ACL 2023)

• Continual Knowledge Distillation for Neural Machine Translation (Zhang et al., ACL 2023)

ACL

• Yuanchi Zhang, Peng Li, Maosong Sun, and Yang Liu. 2023. Continual Knowledge Distillation for Neural Machine Translation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7978–7996, Toronto, Canada. Association for Computational Linguistics.