@inproceedings{you-etal-2024-efficient,
title = "Efficient Domain Adaptation for Non-Autoregressive Machine Translation",
author = "You, WangJie and
Guo, Pei and
Li, Juntao and
Chen, Kehai and
Zhang, Min",
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.810/",
doi = "10.18653/v1/2024.findings-acl.810",
pages = "13657--13670",
abstract = "Domain adaptation remains a challenge in the realm of Neural Machine Translation (NMT), even in the era of large language models (LLMs). Existing non-parametric approaches like nearest neighbor machine translation have made small Autoregressive Translation (AT) models achieve efficient domain generalization and adaptation without updating parameters, but leaving the Non-Autoregressive Translation (NAT) counterparts under-explored. To fill this blank, we introduce $Bi$-$k$NN, an innovative and efficient domain adaptation approach for NAT models that tailors a k-nearest-neighbor algorithm for NAT. Specifically, we introduce an effective datastore construction and correlated updating strategies to conform the parallel nature of NAT. Additionally, we train a meta-network that seamlessly integrates the NN distribution with the NMT distribution robustly during the iterative decoding process of NAT. Our experimental results across four benchmark datasets demonstrate that our $Bi$-$k$NN not only achieves significant improvements over the Base-NAT model (7.8 BLEU on average) but also exhibits enhanced efficiency."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="you-etal-2024-efficient">
<titleInfo>
<title>Efficient Domain Adaptation for Non-Autoregressive Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">WangJie</namePart>
<namePart type="family">You</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pei</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juntao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kehai</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</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>Domain adaptation remains a challenge in the realm of Neural Machine Translation (NMT), even in the era of large language models (LLMs). Existing non-parametric approaches like nearest neighbor machine translation have made small Autoregressive Translation (AT) models achieve efficient domain generalization and adaptation without updating parameters, but leaving the Non-Autoregressive Translation (NAT) counterparts under-explored. To fill this blank, we introduce Bi-kNN, an innovative and efficient domain adaptation approach for NAT models that tailors a k-nearest-neighbor algorithm for NAT. Specifically, we introduce an effective datastore construction and correlated updating strategies to conform the parallel nature of NAT. Additionally, we train a meta-network that seamlessly integrates the NN distribution with the NMT distribution robustly during the iterative decoding process of NAT. Our experimental results across four benchmark datasets demonstrate that our Bi-kNN not only achieves significant improvements over the Base-NAT model (7.8 BLEU on average) but also exhibits enhanced efficiency.</abstract>
<identifier type="citekey">you-etal-2024-efficient</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.810</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.810/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>13657</start>
<end>13670</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficient Domain Adaptation for Non-Autoregressive Machine Translation
%A You, WangJie
%A Guo, Pei
%A Li, Juntao
%A Chen, Kehai
%A Zhang, Min
%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 you-etal-2024-efficient
%X Domain adaptation remains a challenge in the realm of Neural Machine Translation (NMT), even in the era of large language models (LLMs). Existing non-parametric approaches like nearest neighbor machine translation have made small Autoregressive Translation (AT) models achieve efficient domain generalization and adaptation without updating parameters, but leaving the Non-Autoregressive Translation (NAT) counterparts under-explored. To fill this blank, we introduce Bi-kNN, an innovative and efficient domain adaptation approach for NAT models that tailors a k-nearest-neighbor algorithm for NAT. Specifically, we introduce an effective datastore construction and correlated updating strategies to conform the parallel nature of NAT. Additionally, we train a meta-network that seamlessly integrates the NN distribution with the NMT distribution robustly during the iterative decoding process of NAT. Our experimental results across four benchmark datasets demonstrate that our Bi-kNN not only achieves significant improvements over the Base-NAT model (7.8 BLEU on average) but also exhibits enhanced efficiency.
%R 10.18653/v1/2024.findings-acl.810
%U https://aclanthology.org/2024.findings-acl.810/
%U https://doi.org/10.18653/v1/2024.findings-acl.810
%P 13657-13670
Markdown (Informal)
[Efficient Domain Adaptation for Non-Autoregressive Machine Translation](https://aclanthology.org/2024.findings-acl.810/) (You et al., Findings 2024)
ACL