@inproceedings{zhang-xu-2022-byte,
title = "Byte-based Multilingual {NMT} for Endangered Languages",
author = "Zhang, Mengjiao and
Xu, Jia",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.388/",
pages = "4407--4417",
abstract = "Multilingual neural machine translation (MNMT) jointly trains a shared model for translation with multiple language pairs. However, traditional subword-based MNMT approaches suffer from out-of-vocabulary (OOV) issues and representation bottleneck, which often degrades translation performance on certain language pairs. While byte tokenization is used to tackle the OOV problems in neural machine translation (NMT), until now its capability has not been validated in MNMT. Additionally, existing work has not studied how byte encoding can benefit endangered language translation to our knowledge. We propose a byte-based multilingual neural machine translation system (BMNMT) to alleviate the representation bottleneck and improve translation performance in endangered languages. Furthermore, we design a random byte mapping method with an ensemble prediction to enhance our model robustness. Experimental results show that our BMNMT consistently and significantly outperforms subword/word-based baselines on twelve language pairs up to +18.5 BLEU points, an 840{\%} relative improvement."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-xu-2022-byte">
<titleInfo>
<title>Byte-based Multilingual NMT for Endangered Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mengjiao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jia</namePart>
<namePart type="family">Xu</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 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multilingual neural machine translation (MNMT) jointly trains a shared model for translation with multiple language pairs. However, traditional subword-based MNMT approaches suffer from out-of-vocabulary (OOV) issues and representation bottleneck, which often degrades translation performance on certain language pairs. While byte tokenization is used to tackle the OOV problems in neural machine translation (NMT), until now its capability has not been validated in MNMT. Additionally, existing work has not studied how byte encoding can benefit endangered language translation to our knowledge. We propose a byte-based multilingual neural machine translation system (BMNMT) to alleviate the representation bottleneck and improve translation performance in endangered languages. Furthermore, we design a random byte mapping method with an ensemble prediction to enhance our model robustness. Experimental results show that our BMNMT consistently and significantly outperforms subword/word-based baselines on twelve language pairs up to +18.5 BLEU points, an 840% relative improvement.</abstract>
<identifier type="citekey">zhang-xu-2022-byte</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.388/</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>4407</start>
<end>4417</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Byte-based Multilingual NMT for Endangered Languages
%A Zhang, Mengjiao
%A Xu, Jia
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F zhang-xu-2022-byte
%X Multilingual neural machine translation (MNMT) jointly trains a shared model for translation with multiple language pairs. However, traditional subword-based MNMT approaches suffer from out-of-vocabulary (OOV) issues and representation bottleneck, which often degrades translation performance on certain language pairs. While byte tokenization is used to tackle the OOV problems in neural machine translation (NMT), until now its capability has not been validated in MNMT. Additionally, existing work has not studied how byte encoding can benefit endangered language translation to our knowledge. We propose a byte-based multilingual neural machine translation system (BMNMT) to alleviate the representation bottleneck and improve translation performance in endangered languages. Furthermore, we design a random byte mapping method with an ensemble prediction to enhance our model robustness. Experimental results show that our BMNMT consistently and significantly outperforms subword/word-based baselines on twelve language pairs up to +18.5 BLEU points, an 840% relative improvement.
%U https://aclanthology.org/2022.coling-1.388/
%P 4407-4417
Markdown (Informal)
[Byte-based Multilingual NMT for Endangered Languages](https://aclanthology.org/2022.coling-1.388/) (Zhang & Xu, COLING 2022)
ACL
- Mengjiao Zhang and Jia Xu. 2022. Byte-based Multilingual NMT for Endangered Languages. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4407–4417, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.