@inproceedings{poncelas-effendi-2022-benefiting,
title = "Benefiting from Language Similarity in the Multilingual {MT} Training: Case Study of {I}ndonesian and {M}alaysian",
author = "Poncelas, Alberto and
Effendi, Johanes",
editor = "Ojha, Atul Kr. and
Liu, Chao-Hong and
Vylomova, Ekaterina and
Abbott, Jade and
Washington, Jonathan and
Oco, Nathaniel and
Pirinen, Tommi A and
Malykh, Valentin and
Logacheva, Varvara and
Zhao, Xiaobing",
booktitle = "Proceedings of the Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2022)",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.loresmt-1.11",
pages = "84--92",
abstract = "The development of machine translation (MT) has been successful in breaking the language barrier of the world{'}s top 10-20 languages. However, for the rest of it, delivering an acceptable translation quality is still a challenge due to the limited resource. To tackle this problem, most studies focus on augmenting data while overlooking the fact that we can borrow high-quality natural data from the closely-related language. In this work, we propose an MT model training strategy by increasing the language directions as a means of augmentation in a multilingual setting. Our experiment result using Indonesian and Malaysian on the state-of-the-art MT model showcases the effectiveness and robustness of our method.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="poncelas-effendi-2022-benefiting">
<titleInfo>
<title>Benefiting from Language Similarity in the Multilingual MT Training: Case Study of Indonesian and Malaysian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Poncelas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johanes</namePart>
<namePart type="family">Effendi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2022)</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">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">Tommi</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Pirinen</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">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The development of machine translation (MT) has been successful in breaking the language barrier of the world’s top 10-20 languages. However, for the rest of it, delivering an acceptable translation quality is still a challenge due to the limited resource. To tackle this problem, most studies focus on augmenting data while overlooking the fact that we can borrow high-quality natural data from the closely-related language. In this work, we propose an MT model training strategy by increasing the language directions as a means of augmentation in a multilingual setting. Our experiment result using Indonesian and Malaysian on the state-of-the-art MT model showcases the effectiveness and robustness of our method.</abstract>
<identifier type="citekey">poncelas-effendi-2022-benefiting</identifier>
<location>
<url>https://aclanthology.org/2022.loresmt-1.11</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>84</start>
<end>92</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benefiting from Language Similarity in the Multilingual MT Training: Case Study of Indonesian and Malaysian
%A Poncelas, Alberto
%A Effendi, Johanes
%Y Ojha, Atul Kr.
%Y Liu, Chao-Hong
%Y Vylomova, Ekaterina
%Y Abbott, Jade
%Y Washington, Jonathan
%Y Oco, Nathaniel
%Y Pirinen, Tommi A.
%Y Malykh, Valentin
%Y Logacheva, Varvara
%Y Zhao, Xiaobing
%S Proceedings of the Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2022)
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F poncelas-effendi-2022-benefiting
%X The development of machine translation (MT) has been successful in breaking the language barrier of the world’s top 10-20 languages. However, for the rest of it, delivering an acceptable translation quality is still a challenge due to the limited resource. To tackle this problem, most studies focus on augmenting data while overlooking the fact that we can borrow high-quality natural data from the closely-related language. In this work, we propose an MT model training strategy by increasing the language directions as a means of augmentation in a multilingual setting. Our experiment result using Indonesian and Malaysian on the state-of-the-art MT model showcases the effectiveness and robustness of our method.
%U https://aclanthology.org/2022.loresmt-1.11
%P 84-92
Markdown (Informal)
[Benefiting from Language Similarity in the Multilingual MT Training: Case Study of Indonesian and Malaysian](https://aclanthology.org/2022.loresmt-1.11) (Poncelas & Effendi, LoResMT 2022)
ACL