@inproceedings{atrio-etal-2023-simplified,
title = "A Simplified Training Pipeline for Low-Resource and Unsupervised Machine Translation",
author = "Atrio, {\`A}lex R. and
Allemann, Alexis and
Dolamic, Ljiljana and
Popescu-Belis, Andrei",
editor = "Ojha, Atul Kr. and
Liu, Chao-hong and
Vylomova, Ekaterina and
Pirinen, Flammie and
Abbott, Jade and
Washington, Jonathan and
Oco, Nathaniel and
Malykh, Valentin and
Logacheva, Varvara and
Zhao, Xiaobing",
booktitle = "Proceedings of the Sixth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2023)",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.loresmt-1.4",
doi = "10.18653/v1/2023.loresmt-1.4",
pages = "47--58",
abstract = "Training neural MT systems for low-resource language pairs or in unsupervised settings (i.e. with no parallel data) often involves a large number of auxiliary systems. These may include parent systems trained on higher-resource pairs and used for initializing the parameters of child systems, multilingual systems for neighboring languages, and several stages of systems trained on pseudo-parallel data obtained through back-translation. We propose here a simplified pipeline, which we compare to the best submissions to the WMT 2021 Shared Task on Unsupervised MT and Very Low Resource Supervised MT. Our pipeline only needs two parents, two children, one round of back-translation for low-resource directions and two for unsupervised ones and obtains better or similar scores when compared to more complex alternatives.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="atrio-etal-2023-simplified">
<titleInfo>
<title>A Simplified Training Pipeline for Low-Resource and Unsupervised Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Àlex</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Atrio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Allemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ljiljana</namePart>
<namePart type="family">Dolamic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrei</namePart>
<namePart type="family">Popescu-Belis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jade</namePart>
<namePart type="family">Abbott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Washington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Oco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Malykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varvara</namePart>
<namePart type="family">Logacheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobing</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Training neural MT systems for low-resource language pairs or in unsupervised settings (i.e. with no parallel data) often involves a large number of auxiliary systems. These may include parent systems trained on higher-resource pairs and used for initializing the parameters of child systems, multilingual systems for neighboring languages, and several stages of systems trained on pseudo-parallel data obtained through back-translation. We propose here a simplified pipeline, which we compare to the best submissions to the WMT 2021 Shared Task on Unsupervised MT and Very Low Resource Supervised MT. Our pipeline only needs two parents, two children, one round of back-translation for low-resource directions and two for unsupervised ones and obtains better or similar scores when compared to more complex alternatives.</abstract>
<identifier type="citekey">atrio-etal-2023-simplified</identifier>
<identifier type="doi">10.18653/v1/2023.loresmt-1.4</identifier>
<location>
<url>https://aclanthology.org/2023.loresmt-1.4</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>47</start>
<end>58</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Simplified Training Pipeline for Low-Resource and Unsupervised Machine Translation
%A Atrio, Àlex R.
%A Allemann, Alexis
%A Dolamic, Ljiljana
%A Popescu-Belis, Andrei
%Y Ojha, Atul Kr.
%Y Liu, Chao-hong
%Y Vylomova, Ekaterina
%Y Pirinen, Flammie
%Y Abbott, Jade
%Y Washington, Jonathan
%Y Oco, Nathaniel
%Y Malykh, Valentin
%Y Logacheva, Varvara
%Y Zhao, Xiaobing
%S Proceedings of the Sixth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2023)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F atrio-etal-2023-simplified
%X Training neural MT systems for low-resource language pairs or in unsupervised settings (i.e. with no parallel data) often involves a large number of auxiliary systems. These may include parent systems trained on higher-resource pairs and used for initializing the parameters of child systems, multilingual systems for neighboring languages, and several stages of systems trained on pseudo-parallel data obtained through back-translation. We propose here a simplified pipeline, which we compare to the best submissions to the WMT 2021 Shared Task on Unsupervised MT and Very Low Resource Supervised MT. Our pipeline only needs two parents, two children, one round of back-translation for low-resource directions and two for unsupervised ones and obtains better or similar scores when compared to more complex alternatives.
%R 10.18653/v1/2023.loresmt-1.4
%U https://aclanthology.org/2023.loresmt-1.4
%U https://doi.org/10.18653/v1/2023.loresmt-1.4
%P 47-58
Markdown (Informal)
[A Simplified Training Pipeline for Low-Resource and Unsupervised Machine Translation](https://aclanthology.org/2023.loresmt-1.4) (Atrio et al., LoResMT 2023)
ACL