@inproceedings{purason-tattar-2022-multilingual,
title = "Multilingual Neural Machine Translation With the Right Amount of Sharing",
author = {Purason, Taido and
T{\"a}ttar, Andre},
editor = {Moniz, Helena and
Macken, Lieve and
Rufener, Andrew and
Barrault, Lo{\"\i}c and
Costa-juss{\`a}, Marta R. and
Declercq, Christophe and
Koponen, Maarit and
Kemp, Ellie and
Pilos, Spyridon and
Forcada, Mikel L. and
Scarton, Carolina and
Van den Bogaert, Joachim and
Daems, Joke and
Tezcan, Arda and
Vanroy, Bram and
Fonteyne, Margot},
booktitle = "Proceedings of the 23rd Annual Conference of the European Association for Machine Translation",
month = jun,
year = "2022",
address = "Ghent, Belgium",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2022.eamt-1.12",
pages = "91--100",
abstract = "Large multilingual Transformer-based machine translation models have had a pivotal role in making translation systems available for hundreds of languages with good zero-shot translation performance. One such example is the universal model with shared encoder-decoder architecture. Additionally, jointly trained language-specific encoder-decoder systems have been proposed for multilingual neural machine translation (NMT) models. This work investigates various knowledge-sharing approaches on the encoder side while keeping the decoder language- or language-group-specific. We propose a novel approach, where we use universal, language-group-specific and language-specific modules to solve the shortcomings of both the universal models and models with language-specific encoders-decoders. Experiments on a multilingual dataset set up to model real-world scenarios, including zero-shot and low-resource translation, show that our proposed models achieve higher translation quality compared to purely universal and language-specific approaches.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="purason-tattar-2022-multilingual">
<titleInfo>
<title>Multilingual Neural Machine Translation With the Right Amount of Sharing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Taido</namePart>
<namePart type="family">Purason</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Tättar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Annual Conference of the European Association for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lieve</namePart>
<namePart type="family">Macken</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Rufener</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Loïc</namePart>
<namePart type="family">Barrault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christophe</namePart>
<namePart type="family">Declercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maarit</namePart>
<namePart type="family">Koponen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ellie</namePart>
<namePart type="family">Kemp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Spyridon</namePart>
<namePart type="family">Pilos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolina</namePart>
<namePart type="family">Scarton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joachim</namePart>
<namePart type="family">Van den Bogaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joke</namePart>
<namePart type="family">Daems</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arda</namePart>
<namePart type="family">Tezcan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bram</namePart>
<namePart type="family">Vanroy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Margot</namePart>
<namePart type="family">Fonteyne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Ghent, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large multilingual Transformer-based machine translation models have had a pivotal role in making translation systems available for hundreds of languages with good zero-shot translation performance. One such example is the universal model with shared encoder-decoder architecture. Additionally, jointly trained language-specific encoder-decoder systems have been proposed for multilingual neural machine translation (NMT) models. This work investigates various knowledge-sharing approaches on the encoder side while keeping the decoder language- or language-group-specific. We propose a novel approach, where we use universal, language-group-specific and language-specific modules to solve the shortcomings of both the universal models and models with language-specific encoders-decoders. Experiments on a multilingual dataset set up to model real-world scenarios, including zero-shot and low-resource translation, show that our proposed models achieve higher translation quality compared to purely universal and language-specific approaches.</abstract>
<identifier type="citekey">purason-tattar-2022-multilingual</identifier>
<location>
<url>https://aclanthology.org/2022.eamt-1.12</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>91</start>
<end>100</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual Neural Machine Translation With the Right Amount of Sharing
%A Purason, Taido
%A Tättar, Andre
%Y Moniz, Helena
%Y Macken, Lieve
%Y Rufener, Andrew
%Y Barrault, Loïc
%Y Costa-jussà, Marta R.
%Y Declercq, Christophe
%Y Koponen, Maarit
%Y Kemp, Ellie
%Y Pilos, Spyridon
%Y Forcada, Mikel L.
%Y Scarton, Carolina
%Y Van den Bogaert, Joachim
%Y Daems, Joke
%Y Tezcan, Arda
%Y Vanroy, Bram
%Y Fonteyne, Margot
%S Proceedings of the 23rd Annual Conference of the European Association for Machine Translation
%D 2022
%8 June
%I European Association for Machine Translation
%C Ghent, Belgium
%F purason-tattar-2022-multilingual
%X Large multilingual Transformer-based machine translation models have had a pivotal role in making translation systems available for hundreds of languages with good zero-shot translation performance. One such example is the universal model with shared encoder-decoder architecture. Additionally, jointly trained language-specific encoder-decoder systems have been proposed for multilingual neural machine translation (NMT) models. This work investigates various knowledge-sharing approaches on the encoder side while keeping the decoder language- or language-group-specific. We propose a novel approach, where we use universal, language-group-specific and language-specific modules to solve the shortcomings of both the universal models and models with language-specific encoders-decoders. Experiments on a multilingual dataset set up to model real-world scenarios, including zero-shot and low-resource translation, show that our proposed models achieve higher translation quality compared to purely universal and language-specific approaches.
%U https://aclanthology.org/2022.eamt-1.12
%P 91-100
Markdown (Informal)
[Multilingual Neural Machine Translation With the Right Amount of Sharing](https://aclanthology.org/2022.eamt-1.12) (Purason & Tättar, EAMT 2022)
ACL