@inproceedings{zheng-etal-2021-non-parametric,
title = "Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation",
author = "Zheng, Xin and
Zhang, Zhirui and
Huang, Shujian and
Chen, Boxing and
Xie, Jun and
Luo, Weihua and
Chen, Jiajun",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.358",
doi = "10.18653/v1/2021.findings-emnlp.358",
pages = "4234--4241",
abstract = "Recently, kNN-MT (Khandelwal et al., 2020) has shown the promising capability of directly incorporating the pre-trained neural machine translation (NMT) model with domain-specific token-level k-nearest-neighbor (kNN) retrieval to achieve domain adaptation without retraining. Despite being conceptually attractive, it heavily relies on high-quality in-domain parallel corpora, limiting its capability on unsupervised domain adaptation, where in-domain parallel corpora are scarce or nonexistent. In this paper, we propose a novel framework that directly uses in-domain monolingual sentences in the target language to construct an effective datastore for k-nearest-neighbor retrieval. To this end, we first introduce an autoencoder task based on the target language, and then insert lightweight adapters into the original NMT model to map the token-level representation of this task to the ideal representation of the translation task. Experiments on multi-domain datasets demonstrate that our proposed approach significantly improves the translation accuracy with target-side monolingual data, while achieving comparable performance with back-translation. Our implementation is open-sourced at \url{https://github.com/zhengxxn/UDA-KNN}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-etal-2021-non-parametric">
<titleInfo>
<title>Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhirui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shujian</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boxing</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weihua</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Chen</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>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently, kNN-MT (Khandelwal et al., 2020) has shown the promising capability of directly incorporating the pre-trained neural machine translation (NMT) model with domain-specific token-level k-nearest-neighbor (kNN) retrieval to achieve domain adaptation without retraining. Despite being conceptually attractive, it heavily relies on high-quality in-domain parallel corpora, limiting its capability on unsupervised domain adaptation, where in-domain parallel corpora are scarce or nonexistent. In this paper, we propose a novel framework that directly uses in-domain monolingual sentences in the target language to construct an effective datastore for k-nearest-neighbor retrieval. To this end, we first introduce an autoencoder task based on the target language, and then insert lightweight adapters into the original NMT model to map the token-level representation of this task to the ideal representation of the translation task. Experiments on multi-domain datasets demonstrate that our proposed approach significantly improves the translation accuracy with target-side monolingual data, while achieving comparable performance with back-translation. Our implementation is open-sourced at https://github.com/zhengxxn/UDA-KNN.</abstract>
<identifier type="citekey">zheng-etal-2021-non-parametric</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.358</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.358</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>4234</start>
<end>4241</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation
%A Zheng, Xin
%A Zhang, Zhirui
%A Huang, Shujian
%A Chen, Boxing
%A Xie, Jun
%A Luo, Weihua
%A Chen, Jiajun
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F zheng-etal-2021-non-parametric
%X Recently, kNN-MT (Khandelwal et al., 2020) has shown the promising capability of directly incorporating the pre-trained neural machine translation (NMT) model with domain-specific token-level k-nearest-neighbor (kNN) retrieval to achieve domain adaptation without retraining. Despite being conceptually attractive, it heavily relies on high-quality in-domain parallel corpora, limiting its capability on unsupervised domain adaptation, where in-domain parallel corpora are scarce or nonexistent. In this paper, we propose a novel framework that directly uses in-domain monolingual sentences in the target language to construct an effective datastore for k-nearest-neighbor retrieval. To this end, we first introduce an autoencoder task based on the target language, and then insert lightweight adapters into the original NMT model to map the token-level representation of this task to the ideal representation of the translation task. Experiments on multi-domain datasets demonstrate that our proposed approach significantly improves the translation accuracy with target-side monolingual data, while achieving comparable performance with back-translation. Our implementation is open-sourced at https://github.com/zhengxxn/UDA-KNN.
%R 10.18653/v1/2021.findings-emnlp.358
%U https://aclanthology.org/2021.findings-emnlp.358
%U https://doi.org/10.18653/v1/2021.findings-emnlp.358
%P 4234-4241
Markdown (Informal)
[Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation](https://aclanthology.org/2021.findings-emnlp.358) (Zheng et al., Findings 2021)
ACL