@inproceedings{reheman-etal-2024-exploiting,
title = "Exploiting Target Language Data for Neural Machine Translation Beyond Back Translation",
author = "Reheman, Abudurexiti and
Luo, Yingfeng and
Ruan, Junhao and
Zhang, Chunliang and
Ma, Anxiang and
Xiao, Tong and
Zhu, JingBo",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.727/",
doi = "10.18653/v1/2024.findings-acl.727",
pages = "12216--12228",
abstract = "Neural Machine Translation (NMT) encounters challenges when translating in new domains and low-resource languages. To address these issues, researchers have proposed methods to integrate additional knowledge into NMT, such as translation memories (TMs). However, finding TMs that closely match the input sentence remains challenging, particularly in specific domains. On the other hand, monolingual data is widely accessible in most languages, and back-translation is seen as a promising approach for utilizing target language data. Nevertheless, it still necessitates additional training. In this paper, we introduce Pseudo-$k$NN-MT, a variant of $k$-nearest neighbor machine translation ($k$NN-MT) that utilizes target language data by constructing a pseudo datastore. Furthermore, we investigate the utility of large language models (LLMs) for the $k$NN component. Experimental results demonstrate that our approach exhibits strong domain adaptation capability in both high-resource and low-resource machine translation. Notably, LLMs are found to be beneficial for robust NMT systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reheman-etal-2024-exploiting">
<titleInfo>
<title>Exploiting Target Language Data for Neural Machine Translation Beyond Back Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abudurexiti</namePart>
<namePart type="family">Reheman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingfeng</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junhao</namePart>
<namePart type="family">Ruan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chunliang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anxiang</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">JingBo</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural Machine Translation (NMT) encounters challenges when translating in new domains and low-resource languages. To address these issues, researchers have proposed methods to integrate additional knowledge into NMT, such as translation memories (TMs). However, finding TMs that closely match the input sentence remains challenging, particularly in specific domains. On the other hand, monolingual data is widely accessible in most languages, and back-translation is seen as a promising approach for utilizing target language data. Nevertheless, it still necessitates additional training. In this paper, we introduce Pseudo-kNN-MT, a variant of k-nearest neighbor machine translation (kNN-MT) that utilizes target language data by constructing a pseudo datastore. Furthermore, we investigate the utility of large language models (LLMs) for the kNN component. Experimental results demonstrate that our approach exhibits strong domain adaptation capability in both high-resource and low-resource machine translation. Notably, LLMs are found to be beneficial for robust NMT systems.</abstract>
<identifier type="citekey">reheman-etal-2024-exploiting</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.727</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.727/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>12216</start>
<end>12228</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploiting Target Language Data for Neural Machine Translation Beyond Back Translation
%A Reheman, Abudurexiti
%A Luo, Yingfeng
%A Ruan, Junhao
%A Zhang, Chunliang
%A Ma, Anxiang
%A Xiao, Tong
%A Zhu, JingBo
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F reheman-etal-2024-exploiting
%X Neural Machine Translation (NMT) encounters challenges when translating in new domains and low-resource languages. To address these issues, researchers have proposed methods to integrate additional knowledge into NMT, such as translation memories (TMs). However, finding TMs that closely match the input sentence remains challenging, particularly in specific domains. On the other hand, monolingual data is widely accessible in most languages, and back-translation is seen as a promising approach for utilizing target language data. Nevertheless, it still necessitates additional training. In this paper, we introduce Pseudo-kNN-MT, a variant of k-nearest neighbor machine translation (kNN-MT) that utilizes target language data by constructing a pseudo datastore. Furthermore, we investigate the utility of large language models (LLMs) for the kNN component. Experimental results demonstrate that our approach exhibits strong domain adaptation capability in both high-resource and low-resource machine translation. Notably, LLMs are found to be beneficial for robust NMT systems.
%R 10.18653/v1/2024.findings-acl.727
%U https://aclanthology.org/2024.findings-acl.727/
%U https://doi.org/10.18653/v1/2024.findings-acl.727
%P 12216-12228
Markdown (Informal)
[Exploiting Target Language Data for Neural Machine Translation Beyond Back Translation](https://aclanthology.org/2024.findings-acl.727/) (Reheman et al., Findings 2024)
ACL