@inproceedings{martins-etal-2022-efficient,
title = "Efficient Machine Translation Domain Adaptation",
author = "Martins, Pedro and
Marinho, Zita and
Martins, Andre",
editor = "Das, Rajarshi and
Lewis, Patrick and
Min, Sewon and
Thai, June and
Zaheer, Manzil",
booktitle = "Proceedings of the 1st Workshop on Semiparametric Methods in NLP: Decoupling Logic from Knowledge",
month = may,
year = "2022",
address = "Dublin, Ireland and Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.spanlp-1.3",
doi = "10.18653/v1/2022.spanlp-1.3",
pages = "23--29",
abstract = "Machine translation models struggle when translating out-of-domain text, which makes domain adaptation a topic of critical importance. However, most domain adaptation methods focus on fine-tuning or training the entire or part of the model on every new domain, which can be costly. On the other hand, semi-parametric models have been shown to successfully perform domain adaptation by retrieving examples from an in-domain datastore (Khandelwal et al., 2021). A drawback of these retrieval-augmented models, however, is that they tend to be substantially slower. In this paper, we explore several approaches to speed up nearest neighbors machine translation. We adapt the methods recently proposed by He et al. (2021) for language modeling, and introduce a simple but effective caching strategy that avoids performing retrieval when similar contexts have been seen before. Translation quality and runtimes for several domains show the effectiveness of the proposed solutions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="martins-etal-2022-efficient">
<titleInfo>
<title>Efficient Machine Translation Domain Adaptation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zita</namePart>
<namePart type="family">Marinho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</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>Proceedings of the 1st Workshop on Semiparametric Methods in NLP: Decoupling Logic from Knowledge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rajarshi</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Lewis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sewon</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">June</namePart>
<namePart type="family">Thai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manzil</namePart>
<namePart type="family">Zaheer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland and Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Machine translation models struggle when translating out-of-domain text, which makes domain adaptation a topic of critical importance. However, most domain adaptation methods focus on fine-tuning or training the entire or part of the model on every new domain, which can be costly. On the other hand, semi-parametric models have been shown to successfully perform domain adaptation by retrieving examples from an in-domain datastore (Khandelwal et al., 2021). A drawback of these retrieval-augmented models, however, is that they tend to be substantially slower. In this paper, we explore several approaches to speed up nearest neighbors machine translation. We adapt the methods recently proposed by He et al. (2021) for language modeling, and introduce a simple but effective caching strategy that avoids performing retrieval when similar contexts have been seen before. Translation quality and runtimes for several domains show the effectiveness of the proposed solutions.</abstract>
<identifier type="citekey">martins-etal-2022-efficient</identifier>
<identifier type="doi">10.18653/v1/2022.spanlp-1.3</identifier>
<location>
<url>https://aclanthology.org/2022.spanlp-1.3</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>23</start>
<end>29</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficient Machine Translation Domain Adaptation
%A Martins, Pedro
%A Marinho, Zita
%A Martins, Andre
%Y Das, Rajarshi
%Y Lewis, Patrick
%Y Min, Sewon
%Y Thai, June
%Y Zaheer, Manzil
%S Proceedings of the 1st Workshop on Semiparametric Methods in NLP: Decoupling Logic from Knowledge
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland and Online
%F martins-etal-2022-efficient
%X Machine translation models struggle when translating out-of-domain text, which makes domain adaptation a topic of critical importance. However, most domain adaptation methods focus on fine-tuning or training the entire or part of the model on every new domain, which can be costly. On the other hand, semi-parametric models have been shown to successfully perform domain adaptation by retrieving examples from an in-domain datastore (Khandelwal et al., 2021). A drawback of these retrieval-augmented models, however, is that they tend to be substantially slower. In this paper, we explore several approaches to speed up nearest neighbors machine translation. We adapt the methods recently proposed by He et al. (2021) for language modeling, and introduce a simple but effective caching strategy that avoids performing retrieval when similar contexts have been seen before. Translation quality and runtimes for several domains show the effectiveness of the proposed solutions.
%R 10.18653/v1/2022.spanlp-1.3
%U https://aclanthology.org/2022.spanlp-1.3
%U https://doi.org/10.18653/v1/2022.spanlp-1.3
%P 23-29
Markdown (Informal)
[Efficient Machine Translation Domain Adaptation](https://aclanthology.org/2022.spanlp-1.3) (Martins et al., SpaNLP 2022)
ACL
- Pedro Martins, Zita Marinho, and Andre Martins. 2022. Efficient Machine Translation Domain Adaptation. In Proceedings of the 1st Workshop on Semiparametric Methods in NLP: Decoupling Logic from Knowledge, pages 23–29, Dublin, Ireland and Online. Association for Computational Linguistics.