<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vu-etal-2021-generalised">
    <titleInfo>
        <title>Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection</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">Xuanli</namePart>
        <namePart type="family">He</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>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper considers the unsupervised domain adaptation problem for neural machine translation (NMT), where we assume the access to only monolingual text in either the source or target language in the new domain. We propose a cross-lingual data selection method to extract in-domain sentences in the missing language side from a large generic monolingual corpus. Our proposed method trains an adaptive layer on top of multilingual BERT by contrastive learning to align the representation between the source and target language. This then enables the transferability of the domain classifier between the languages in a zero-shot manner. Once the in-domain data is detected by the classifier, the NMT model is then adapted to the new domain by jointly learning translation and domain discrimination tasks. We evaluate our cross-lingual data selection method on NMT across five diverse domains in three language pairs, as well as a real-world scenario of translation for COVID-19. The results show that our proposed method outperforms other selection baselines up to +1.5 BLEU score.</abstract>
    <identifier type="citekey">vu-etal-2021-generalised</identifier>
    <identifier type="doi">10.18653/v1/2021.emnlp-main.268</identifier>
    <location>
        <url>https://aclanthology.org/2021.emnlp-main.268</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>3335</start>
            <end>3346</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection
%A Vu, Thuy-Trang
%A He, Xuanli
%A Phung, Dinh
%A Haffari, Gholamreza
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F vu-etal-2021-generalised
%X This paper considers the unsupervised domain adaptation problem for neural machine translation (NMT), where we assume the access to only monolingual text in either the source or target language in the new domain. We propose a cross-lingual data selection method to extract in-domain sentences in the missing language side from a large generic monolingual corpus. Our proposed method trains an adaptive layer on top of multilingual BERT by contrastive learning to align the representation between the source and target language. This then enables the transferability of the domain classifier between the languages in a zero-shot manner. Once the in-domain data is detected by the classifier, the NMT model is then adapted to the new domain by jointly learning translation and domain discrimination tasks. We evaluate our cross-lingual data selection method on NMT across five diverse domains in three language pairs, as well as a real-world scenario of translation for COVID-19. The results show that our proposed method outperforms other selection baselines up to +1.5 BLEU score.
%R 10.18653/v1/2021.emnlp-main.268
%U https://aclanthology.org/2021.emnlp-main.268
%U https://doi.org/10.18653/v1/2021.emnlp-main.268
%P 3335-3346

Markdown (Informal)

[Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection](https://aclanthology.org/2021.emnlp-main.268) (Vu et al., EMNLP 2021)

• Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection (Vu et al., EMNLP 2021)

ACL

• Thuy-Trang Vu, Xuanli He, Dinh Phung, and Gholamreza Haffari. 2021. Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3335–3346, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.