@inproceedings{lakew-etal-2019-adapting,
title = "Adapting Multilingual Neural Machine Translation to Unseen Languages",
author = "Lakew, Surafel M. and
Karakanta, Alina and
Federico, Marcello and
Negri, Matteo and
Turchi, Marco",
editor = {Niehues, Jan and
Cattoni, Rolando and
St{\"u}ker, Sebastian and
Negri, Matteo and
Turchi, Marco and
Ha, Thanh-Le and
Salesky, Elizabeth and
Sanabria, Ramon and
Barrault, Loic and
Specia, Lucia and
Federico, Marcello},
booktitle = "Proceedings of the 16th International Conference on Spoken Language Translation",
month = nov # " 2-3",
year = "2019",
address = "Hong Kong",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2019.iwslt-1.16/",
abstract = "Multilingual Neural Machine Translation (MNMT) for low- resource languages (LRL) can be enhanced by the presence of related high-resource languages (HRL), but the relatedness of HRL usually relies on predefined linguistic assumptions about language similarity. Recently, adapting MNMT to a LRL has shown to greatly improve performance. In this work, we explore the problem of adapting an MNMT model to an unseen LRL using data selection and model adapta- tion. In order to improve NMT for LRL, we employ perplexity to select HRL data that are most similar to the LRL on the basis of language distance. We extensively explore data selection in popular multilingual NMT settings, namely in (zero-shot) translation, and in adaptation from a multilingual pre-trained model, for both directions (LRL{\ensuremath{\leftrightarrow}}en). We further show that dynamic adaptation of the model`s vocabulary results in a more favourable segmentation for the LRL in comparison with direct adaptation. Experiments show re- ductions in training time and significant performance gains over LRL baselines, even with zero LRL data (+13.0 BLEU), up to +17.0 BLEU for pre-trained multilingual model dynamic adaptation with related data selection. Our method outperforms current approaches, such as massively multilingual models and data augmentation, on four LRL."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lakew-etal-2019-adapting">
<titleInfo>
<title>Adapting Multilingual Neural Machine Translation to Unseen Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Surafel</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Lakew</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Karakanta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-nov 2-3</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Conference on Spoken Language Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Niehues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rolando</namePart>
<namePart type="family">Cattoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Stüker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thanh-Le</namePart>
<namePart type="family">Ha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramon</namePart>
<namePart type="family">Sanabria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Loic</namePart>
<namePart type="family">Barrault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multilingual Neural Machine Translation (MNMT) for low- resource languages (LRL) can be enhanced by the presence of related high-resource languages (HRL), but the relatedness of HRL usually relies on predefined linguistic assumptions about language similarity. Recently, adapting MNMT to a LRL has shown to greatly improve performance. In this work, we explore the problem of adapting an MNMT model to an unseen LRL using data selection and model adapta- tion. In order to improve NMT for LRL, we employ perplexity to select HRL data that are most similar to the LRL on the basis of language distance. We extensively explore data selection in popular multilingual NMT settings, namely in (zero-shot) translation, and in adaptation from a multilingual pre-trained model, for both directions (LRL\ensuremathłeftrightarrowen). We further show that dynamic adaptation of the model‘s vocabulary results in a more favourable segmentation for the LRL in comparison with direct adaptation. Experiments show re- ductions in training time and significant performance gains over LRL baselines, even with zero LRL data (+13.0 BLEU), up to +17.0 BLEU for pre-trained multilingual model dynamic adaptation with related data selection. Our method outperforms current approaches, such as massively multilingual models and data augmentation, on four LRL.</abstract>
<identifier type="citekey">lakew-etal-2019-adapting</identifier>
<location>
<url>https://aclanthology.org/2019.iwslt-1.16/</url>
</location>
<part>
<date>2019-nov 2-3</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adapting Multilingual Neural Machine Translation to Unseen Languages
%A Lakew, Surafel M.
%A Karakanta, Alina
%A Federico, Marcello
%A Negri, Matteo
%A Turchi, Marco
%Y Niehues, Jan
%Y Cattoni, Rolando
%Y Stüker, Sebastian
%Y Negri, Matteo
%Y Turchi, Marco
%Y Ha, Thanh-Le
%Y Salesky, Elizabeth
%Y Sanabria, Ramon
%Y Barrault, Loic
%Y Specia, Lucia
%Y Federico, Marcello
%S Proceedings of the 16th International Conference on Spoken Language Translation
%D 2019
%8 nov 2 3
%I Association for Computational Linguistics
%C Hong Kong
%F lakew-etal-2019-adapting
%X Multilingual Neural Machine Translation (MNMT) for low- resource languages (LRL) can be enhanced by the presence of related high-resource languages (HRL), but the relatedness of HRL usually relies on predefined linguistic assumptions about language similarity. Recently, adapting MNMT to a LRL has shown to greatly improve performance. In this work, we explore the problem of adapting an MNMT model to an unseen LRL using data selection and model adapta- tion. In order to improve NMT for LRL, we employ perplexity to select HRL data that are most similar to the LRL on the basis of language distance. We extensively explore data selection in popular multilingual NMT settings, namely in (zero-shot) translation, and in adaptation from a multilingual pre-trained model, for both directions (LRL\ensuremathłeftrightarrowen). We further show that dynamic adaptation of the model‘s vocabulary results in a more favourable segmentation for the LRL in comparison with direct adaptation. Experiments show re- ductions in training time and significant performance gains over LRL baselines, even with zero LRL data (+13.0 BLEU), up to +17.0 BLEU for pre-trained multilingual model dynamic adaptation with related data selection. Our method outperforms current approaches, such as massively multilingual models and data augmentation, on four LRL.
%U https://aclanthology.org/2019.iwslt-1.16/
Markdown (Informal)
[Adapting Multilingual Neural Machine Translation to Unseen Languages](https://aclanthology.org/2019.iwslt-1.16/) (Lakew et al., IWSLT 2019)
ACL