<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vu-etal-2022-domain">
    <titleInfo>
        <title>Domain Generalisation of NMT: Fusing Adapters with Leave-One-Domain-Out Training</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Thuy-Trang</namePart>
        <namePart type="family">Vu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shahram</namePart>
        <namePart type="family">Khadivi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dinh</namePart>
        <namePart type="family">Phung</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gholamreza</namePart>
        <namePart type="family">Haffari</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2022</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Smaranda</namePart>
            <namePart type="family">Muresan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Preslav</namePart>
            <namePart type="family">Nakov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aline</namePart>
            <namePart type="family">Villavicencio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dublin, Ireland</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Generalising to unseen domains is under-explored and remains a challenge in neural machine translation. Inspired by recent research in parameter-efficient transfer learning from pretrained models, this paper proposes a fusion-based generalisation method that learns to combine domain-specific parameters. We propose a leave-one-domain-out training strategy to avoid information leaking to address the challenge of not knowing the test domain during training time. Empirical results on three language pairs show that our proposed fusion method outperforms other baselines up to +0.8 BLEU score on average.</abstract>
    <identifier type="citekey">vu-etal-2022-domain</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-acl.49</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-acl.49</url>
    </location>
    <part>
        <date>2022-05</date>
        <extent unit="page">
            <start>582</start>
            <end>588</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Domain Generalisation of NMT: Fusing Adapters with Leave-One-Domain-Out Training
%A Vu, Thuy-Trang
%A Khadivi, Shahram
%A Phung, Dinh
%A Haffari, Gholamreza
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F vu-etal-2022-domain
%X Generalising to unseen domains is under-explored and remains a challenge in neural machine translation. Inspired by recent research in parameter-efficient transfer learning from pretrained models, this paper proposes a fusion-based generalisation method that learns to combine domain-specific parameters. We propose a leave-one-domain-out training strategy to avoid information leaking to address the challenge of not knowing the test domain during training time. Empirical results on three language pairs show that our proposed fusion method outperforms other baselines up to +0.8 BLEU score on average.
%R 10.18653/v1/2022.findings-acl.49
%U https://aclanthology.org/2022.findings-acl.49
%U https://doi.org/10.18653/v1/2022.findings-acl.49
%P 582-588

Markdown (Informal)

[Domain Generalisation of NMT: Fusing Adapters with Leave-One-Domain-Out Training](https://aclanthology.org/2022.findings-acl.49) (Vu et al., Findings 2022)

• Domain Generalisation of NMT: Fusing Adapters with Leave-One-Domain-Out Training (Vu et al., Findings 2022)

ACL

• Thuy-Trang Vu, Shahram Khadivi, Dinh Phung, and Gholamreza Haffari. 2022. Domain Generalisation of NMT: Fusing Adapters with Leave-One-Domain-Out Training. In Findings of the Association for Computational Linguistics: ACL 2022, pages 582–588, Dublin, Ireland. Association for Computational Linguistics.