@inproceedings{dabre-chakrabarty-2021-nict,
title = "{NICT}-5`s Submission To {WAT} 2021: {MBART} Pre-training And In-Domain Fine Tuning For Indic Languages",
author = "Dabre, Raj and
Chakrabarty, Abhisek",
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-1.23/",
doi = "10.18653/v1/2021.wat-1.23",
pages = "198--204",
abstract = "In this paper we describe our submission to the multilingual Indic language translation wtask {\textquotedblleft}MultiIndicMT{\textquotedblright} under the team name {\textquotedblleft}NICT-5{\textquotedblright}. This task involves translation from 10 Indic languages into English and vice-versa. The objective of the task was to explore the utility of multilingual approaches using a variety of in-domain and out-of-domain parallel and monolingual corpora. Given the recent success of multilingual NMT pre-training we decided to explore pre-training an MBART model on a large monolingual corpus collection covering all languages in this task followed by multilingual fine-tuning on small in-domain corpora. Firstly, we observed that a small amount of pre-training followed by fine-tuning on small bilingual corpora can yield large gains over when pre-training is not used. Furthermore, multilingual fine-tuning leads to further gains in translation quality which significantly outperforms a very strong multilingual baseline that does not rely on any pre-training."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dabre-chakrabarty-2021-nict">
<titleInfo>
<title>NICT-5‘s Submission To WAT 2021: MBART Pre-training And In-Domain Fine Tuning For Indic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Dabre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhisek</namePart>
<namePart type="family">Chakrabarty</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 describe our submission to the multilingual Indic language translation wtask “MultiIndicMT” under the team name “NICT-5”. This task involves translation from 10 Indic languages into English and vice-versa. The objective of the task was to explore the utility of multilingual approaches using a variety of in-domain and out-of-domain parallel and monolingual corpora. Given the recent success of multilingual NMT pre-training we decided to explore pre-training an MBART model on a large monolingual corpus collection covering all languages in this task followed by multilingual fine-tuning on small in-domain corpora. Firstly, we observed that a small amount of pre-training followed by fine-tuning on small bilingual corpora can yield large gains over when pre-training is not used. Furthermore, multilingual fine-tuning leads to further gains in translation quality which significantly outperforms a very strong multilingual baseline that does not rely on any pre-training.</abstract>
<identifier type="citekey">dabre-chakrabarty-2021-nict</identifier>
<identifier type="doi">10.18653/v1/2021.wat-1.23</identifier>
<location>
<url>https://aclanthology.org/2021.wat-1.23/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>198</start>
<end>204</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NICT-5‘s Submission To WAT 2021: MBART Pre-training And In-Domain Fine Tuning For Indic Languages
%A Dabre, Raj
%A Chakrabarty, Abhisek
%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 dabre-chakrabarty-2021-nict
%X In this paper we describe our submission to the multilingual Indic language translation wtask “MultiIndicMT” under the team name “NICT-5”. This task involves translation from 10 Indic languages into English and vice-versa. The objective of the task was to explore the utility of multilingual approaches using a variety of in-domain and out-of-domain parallel and monolingual corpora. Given the recent success of multilingual NMT pre-training we decided to explore pre-training an MBART model on a large monolingual corpus collection covering all languages in this task followed by multilingual fine-tuning on small in-domain corpora. Firstly, we observed that a small amount of pre-training followed by fine-tuning on small bilingual corpora can yield large gains over when pre-training is not used. Furthermore, multilingual fine-tuning leads to further gains in translation quality which significantly outperforms a very strong multilingual baseline that does not rely on any pre-training.
%R 10.18653/v1/2021.wat-1.23
%U https://aclanthology.org/2021.wat-1.23/
%U https://doi.org/10.18653/v1/2021.wat-1.23
%P 198-204
Markdown (Informal)
[NICT-5’s Submission To WAT 2021: MBART Pre-training And In-Domain Fine Tuning For Indic Languages](https://aclanthology.org/2021.wat-1.23/) (Dabre & Chakrabarty, WAT 2021)
ACL