@inproceedings{susanto-etal-2021-rakutens,
title = "Rakuten{'}s Participation in {WAT} 2021: Examining the Effectiveness of Pre-trained Models for Multilingual and Multimodal Machine Translation",
author = "Susanto, Raymond Hendy and
Wang, Dongzhe and
Yadav, Sunil and
Jain, Mausam and
Htun, Ohnmar",
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-1.9",
doi = "10.18653/v1/2021.wat-1.9",
pages = "96--105",
abstract = "This paper introduces our neural machine translation systems{'} participation in the WAT 2021 shared translation tasks (team ID: sakura). We participated in the (i) NICT-SAP, (ii) Japanese-English multimodal translation, (iii) Multilingual Indic, and (iv) Myanmar-English translation tasks. Multilingual approaches such as mBART (Liu et al., 2020) are capable of pre-training a complete, multilingual sequence-to-sequence model through denoising objectives, making it a great starting point for building multilingual translation systems. Our main focus in this work is to investigate the effectiveness of multilingual finetuning on such a multilingual language model on various translation tasks, including low-resource, multimodal, and mixed-domain translation. We further explore a multimodal approach based on universal visual representation (Zhang et al., 2019) and compare its performance against a unimodal approach based on mBART alone.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="susanto-etal-2021-rakutens">
<titleInfo>
<title>Rakuten’s Participation in WAT 2021: Examining the Effectiveness of Pre-trained Models for Multilingual and Multimodal Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raymond</namePart>
<namePart type="given">Hendy</namePart>
<namePart type="family">Susanto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongzhe</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunil</namePart>
<namePart type="family">Yadav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mausam</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ohnmar</namePart>
<namePart type="family">Htun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-aug</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Asian Translation (WAT2021)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces our neural machine translation systems’ participation in the WAT 2021 shared translation tasks (team ID: sakura). We participated in the (i) NICT-SAP, (ii) Japanese-English multimodal translation, (iii) Multilingual Indic, and (iv) Myanmar-English translation tasks. Multilingual approaches such as mBART (Liu et al., 2020) are capable of pre-training a complete, multilingual sequence-to-sequence model through denoising objectives, making it a great starting point for building multilingual translation systems. Our main focus in this work is to investigate the effectiveness of multilingual finetuning on such a multilingual language model on various translation tasks, including low-resource, multimodal, and mixed-domain translation. We further explore a multimodal approach based on universal visual representation (Zhang et al., 2019) and compare its performance against a unimodal approach based on mBART alone.</abstract>
<identifier type="citekey">susanto-etal-2021-rakutens</identifier>
<identifier type="doi">10.18653/v1/2021.wat-1.9</identifier>
<location>
<url>https://aclanthology.org/2021.wat-1.9</url>
</location>
<part>
<date>2021-aug</date>
<extent unit="page">
<start>96</start>
<end>105</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rakuten’s Participation in WAT 2021: Examining the Effectiveness of Pre-trained Models for Multilingual and Multimodal Machine Translation
%A Susanto, Raymond Hendy
%A Wang, Dongzhe
%A Yadav, Sunil
%A Jain, Mausam
%A Htun, Ohnmar
%S Proceedings of the 8th Workshop on Asian Translation (WAT2021)
%D 2021
%8 aug
%I Association for Computational Linguistics
%C Online
%F susanto-etal-2021-rakutens
%X This paper introduces our neural machine translation systems’ participation in the WAT 2021 shared translation tasks (team ID: sakura). We participated in the (i) NICT-SAP, (ii) Japanese-English multimodal translation, (iii) Multilingual Indic, and (iv) Myanmar-English translation tasks. Multilingual approaches such as mBART (Liu et al., 2020) are capable of pre-training a complete, multilingual sequence-to-sequence model through denoising objectives, making it a great starting point for building multilingual translation systems. Our main focus in this work is to investigate the effectiveness of multilingual finetuning on such a multilingual language model on various translation tasks, including low-resource, multimodal, and mixed-domain translation. We further explore a multimodal approach based on universal visual representation (Zhang et al., 2019) and compare its performance against a unimodal approach based on mBART alone.
%R 10.18653/v1/2021.wat-1.9
%U https://aclanthology.org/2021.wat-1.9
%U https://doi.org/10.18653/v1/2021.wat-1.9
%P 96-105
Markdown (Informal)
[Rakuten’s Participation in WAT 2021: Examining the Effectiveness of Pre-trained Models for Multilingual and Multimodal Machine Translation](https://aclanthology.org/2021.wat-1.9) (Susanto et al., WAT 2021)
ACL