@inproceedings{lakew-etal-2018-neural,
title = "Neural Machine Translation into Language Varieties",
author = "Lakew, Surafel Melaku and
Erofeeva, Aliia and
Federico, Marcello",
editor = "Bojar, Ond{\v{r}}ej and
Chatterjee, Rajen and
Federmann, Christian and
Fishel, Mark and
Graham, Yvette and
Haddow, Barry and
Huck, Matthias and
Yepes, Antonio Jimeno and
Koehn, Philipp and
Monz, Christof and
Negri, Matteo and
N{\'e}v{\'e}ol, Aur{\'e}lie and
Neves, Mariana and
Post, Matt and
Specia, Lucia and
Turchi, Marco and
Verspoor, Karin",
booktitle = "Proceedings of the Third Conference on Machine Translation: Research Papers",
month = oct,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6316",
doi = "10.18653/v1/W18-6316",
pages = "156--164",
abstract = "Both research and commercial machine translation have so far neglected the importance of properly handling the spelling, lexical and grammar divergences occurring among language varieties. Notable cases are standard national varieties such as Brazilian and European Portuguese, and Canadian and European French, which popular online machine translation services are not keeping distinct. We show that an evident side effect of modeling such varieties as unique classes is the generation of inconsistent translations. In this work, we investigate the problem of training neural machine translation from English to specific pairs of language varieties, assuming both labeled and unlabeled parallel texts, and low-resource conditions. We report experiments from English to two pairs of dialects, European-Brazilian Portuguese and European-Canadian French, and two pairs of standardized varieties, Croatian-Serbian and Indonesian-Malay. We show significant BLEU score improvements over baseline systems when translation into similar languages is learned as a multilingual task with shared representations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lakew-etal-2018-neural">
<titleInfo>
<title>Neural Machine Translation into Language Varieties</title>
</titleInfo>
<name type="personal">
<namePart type="given">Surafel</namePart>
<namePart type="given">Melaku</namePart>
<namePart type="family">Lakew</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aliia</namePart>
<namePart type="family">Erofeeva</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>
<originInfo>
<dateIssued>2018-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Conference on Machine Translation: Research Papers</title>
</titleInfo>
<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">Rajen</namePart>
<namePart type="family">Chatterjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Federmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Huck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="given">Jimeno</namePart>
<namePart type="family">Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</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">Aurélie</namePart>
<namePart type="family">Névéol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariana</namePart>
<namePart type="family">Neves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matt</namePart>
<namePart type="family">Post</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">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karin</namePart>
<namePart type="family">Verspoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Both research and commercial machine translation have so far neglected the importance of properly handling the spelling, lexical and grammar divergences occurring among language varieties. Notable cases are standard national varieties such as Brazilian and European Portuguese, and Canadian and European French, which popular online machine translation services are not keeping distinct. We show that an evident side effect of modeling such varieties as unique classes is the generation of inconsistent translations. In this work, we investigate the problem of training neural machine translation from English to specific pairs of language varieties, assuming both labeled and unlabeled parallel texts, and low-resource conditions. We report experiments from English to two pairs of dialects, European-Brazilian Portuguese and European-Canadian French, and two pairs of standardized varieties, Croatian-Serbian and Indonesian-Malay. We show significant BLEU score improvements over baseline systems when translation into similar languages is learned as a multilingual task with shared representations.</abstract>
<identifier type="citekey">lakew-etal-2018-neural</identifier>
<identifier type="doi">10.18653/v1/W18-6316</identifier>
<location>
<url>https://aclanthology.org/W18-6316</url>
</location>
<part>
<date>2018-10</date>
<extent unit="page">
<start>156</start>
<end>164</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Machine Translation into Language Varieties
%A Lakew, Surafel Melaku
%A Erofeeva, Aliia
%A Federico, Marcello
%Y Bojar, Ondřej
%Y Chatterjee, Rajen
%Y Federmann, Christian
%Y Fishel, Mark
%Y Graham, Yvette
%Y Haddow, Barry
%Y Huck, Matthias
%Y Yepes, Antonio Jimeno
%Y Koehn, Philipp
%Y Monz, Christof
%Y Negri, Matteo
%Y Névéol, Aurélie
%Y Neves, Mariana
%Y Post, Matt
%Y Specia, Lucia
%Y Turchi, Marco
%Y Verspoor, Karin
%S Proceedings of the Third Conference on Machine Translation: Research Papers
%D 2018
%8 October
%I Association for Computational Linguistics
%C Brussels, Belgium
%F lakew-etal-2018-neural
%X Both research and commercial machine translation have so far neglected the importance of properly handling the spelling, lexical and grammar divergences occurring among language varieties. Notable cases are standard national varieties such as Brazilian and European Portuguese, and Canadian and European French, which popular online machine translation services are not keeping distinct. We show that an evident side effect of modeling such varieties as unique classes is the generation of inconsistent translations. In this work, we investigate the problem of training neural machine translation from English to specific pairs of language varieties, assuming both labeled and unlabeled parallel texts, and low-resource conditions. We report experiments from English to two pairs of dialects, European-Brazilian Portuguese and European-Canadian French, and two pairs of standardized varieties, Croatian-Serbian and Indonesian-Malay. We show significant BLEU score improvements over baseline systems when translation into similar languages is learned as a multilingual task with shared representations.
%R 10.18653/v1/W18-6316
%U https://aclanthology.org/W18-6316
%U https://doi.org/10.18653/v1/W18-6316
%P 156-164
Markdown (Informal)
[Neural Machine Translation into Language Varieties](https://aclanthology.org/W18-6316) (Lakew et al., WMT 2018)
ACL
- Surafel Melaku Lakew, Aliia Erofeeva, and Marcello Federico. 2018. Neural Machine Translation into Language Varieties. In Proceedings of the Third Conference on Machine Translation: Research Papers, pages 156–164, Brussels, Belgium. Association for Computational Linguistics.