@inproceedings{imamura-sumita-2021-nict,
title = "{NICT}-2 Translation System at {WAT}-2021: Applying a Pretrained Multilingual Encoder-Decoder Model to Low-resource Language Pairs",
author = "Imamura, Kenji and
Sumita, Eiichiro",
editor = "Nakazawa, Toshiaki and
Nakayama, Hideki and
Goto, Isao and
Mino, Hideya and
Ding, Chenchen and
Dabre, Raj and
Kunchukuttan, Anoop and
Higashiyama, Shohei and
Manabe, Hiroshi and
Pa, Win Pa and
Parida, Shantipriya and
Bojar, Ond{\v{r}}ej and
Chu, Chenhui and
Eriguchi, Akiko and
Abe, Kaori and
Oda, Yusuke and
Sudoh, Katsuhito and
Kurohashi, Sadao and
Bhattacharyya, Pushpak",
booktitle = "Proceedings of the 8th Workshop on Asian Translation (WAT2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wat-1.8/",
doi = "10.18653/v1/2021.wat-1.8",
pages = "90--95",
abstract = "In this paper, we present the NICT system (NICT-2) submitted to the NICT-SAP shared task at the 8th Workshop on Asian Translation (WAT-2021). A feature of our system is that we used a pretrained multilingual BART (Bidirectional and Auto-Regressive Transformer; mBART) model. Because publicly available models do not support some languages in the NICT-SAP task, we added these languages to the mBART model and then trained it using monolingual corpora extracted from Wikipedia. We fine-tuned the expanded mBART model using the parallel corpora specified by the NICT-SAP task. The BLEU scores greatly improved in comparison with those of systems without the pretrained model, including the additional languages."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="imamura-sumita-2021-nict">
<titleInfo>
<title>NICT-2 Translation System at WAT-2021: Applying a Pretrained Multilingual Encoder-Decoder Model to Low-resource Language Pairs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kenji</namePart>
<namePart type="family">Imamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiichiro</namePart>
<namePart type="family">Sumita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Asian Translation (WAT2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Toshiaki</namePart>
<namePart type="family">Nakazawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideki</namePart>
<namePart type="family">Nakayama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isao</namePart>
<namePart type="family">Goto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideya</namePart>
<namePart type="family">Mino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenchen</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Dabre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kunchukuttan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shohei</namePart>
<namePart type="family">Higashiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroshi</namePart>
<namePart type="family">Manabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Win</namePart>
<namePart type="given">Pa</namePart>
<namePart type="family">Pa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shantipriya</namePart>
<namePart type="family">Parida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenhui</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akiko</namePart>
<namePart type="family">Eriguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaori</namePart>
<namePart type="family">Abe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Oda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katsuhito</namePart>
<namePart type="family">Sudoh</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">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present the NICT system (NICT-2) submitted to the NICT-SAP shared task at the 8th Workshop on Asian Translation (WAT-2021). A feature of our system is that we used a pretrained multilingual BART (Bidirectional and Auto-Regressive Transformer; mBART) model. Because publicly available models do not support some languages in the NICT-SAP task, we added these languages to the mBART model and then trained it using monolingual corpora extracted from Wikipedia. We fine-tuned the expanded mBART model using the parallel corpora specified by the NICT-SAP task. The BLEU scores greatly improved in comparison with those of systems without the pretrained model, including the additional languages.</abstract>
<identifier type="citekey">imamura-sumita-2021-nict</identifier>
<identifier type="doi">10.18653/v1/2021.wat-1.8</identifier>
<location>
<url>https://aclanthology.org/2021.wat-1.8/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>90</start>
<end>95</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NICT-2 Translation System at WAT-2021: Applying a Pretrained Multilingual Encoder-Decoder Model to Low-resource Language Pairs
%A Imamura, Kenji
%A Sumita, Eiichiro
%Y Nakazawa, Toshiaki
%Y Nakayama, Hideki
%Y Goto, Isao
%Y Mino, Hideya
%Y Ding, Chenchen
%Y Dabre, Raj
%Y Kunchukuttan, Anoop
%Y Higashiyama, Shohei
%Y Manabe, Hiroshi
%Y Pa, Win Pa
%Y Parida, Shantipriya
%Y Bojar, Ondřej
%Y Chu, Chenhui
%Y Eriguchi, Akiko
%Y Abe, Kaori
%Y Oda, Yusuke
%Y Sudoh, Katsuhito
%Y Kurohashi, Sadao
%Y Bhattacharyya, Pushpak
%S Proceedings of the 8th Workshop on Asian Translation (WAT2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F imamura-sumita-2021-nict
%X In this paper, we present the NICT system (NICT-2) submitted to the NICT-SAP shared task at the 8th Workshop on Asian Translation (WAT-2021). A feature of our system is that we used a pretrained multilingual BART (Bidirectional and Auto-Regressive Transformer; mBART) model. Because publicly available models do not support some languages in the NICT-SAP task, we added these languages to the mBART model and then trained it using monolingual corpora extracted from Wikipedia. We fine-tuned the expanded mBART model using the parallel corpora specified by the NICT-SAP task. The BLEU scores greatly improved in comparison with those of systems without the pretrained model, including the additional languages.
%R 10.18653/v1/2021.wat-1.8
%U https://aclanthology.org/2021.wat-1.8/
%U https://doi.org/10.18653/v1/2021.wat-1.8
%P 90-95
Markdown (Informal)
[NICT-2 Translation System at WAT-2021: Applying a Pretrained Multilingual Encoder-Decoder Model to Low-resource Language Pairs](https://aclanthology.org/2021.wat-1.8/) (Imamura & Sumita, WAT 2021)
ACL