@inproceedings{zaninello-birch-2020-multiword,
title = "Multiword Expression aware Neural Machine Translation",
author = "Zaninello, Andrea and
Birch, Alexandra",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.471",
pages = "3816--3825",
abstract = "Multiword Expressions (MWEs) are a frequently occurring phenomenon found in all natural languages that is of great importance to linguistic theory, natural language processing applications, and machine translation systems. Neural Machine Translation (NMT) architectures do not handle these expressions well and previous studies have rarely addressed MWEs in this framework. In this work, we show that annotation and data augmentation, using external linguistic resources, can improve both translation of MWEs that occur in the source, and the generation of MWEs on the target, and increase performance by up to 5.09 BLEU points on MWE test sets. We also devise a MWE score to specifically assess the quality of MWE translation which agrees with human evaluation. We make available the MWE score implementation {--} along with MWE-annotated training sets and corpus-based lists of MWEs {--} for reproduction and extension.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zaninello-birch-2020-multiword">
<titleInfo>
<title>Multiword Expression aware Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Zaninello</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Birch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Multiword Expressions (MWEs) are a frequently occurring phenomenon found in all natural languages that is of great importance to linguistic theory, natural language processing applications, and machine translation systems. Neural Machine Translation (NMT) architectures do not handle these expressions well and previous studies have rarely addressed MWEs in this framework. In this work, we show that annotation and data augmentation, using external linguistic resources, can improve both translation of MWEs that occur in the source, and the generation of MWEs on the target, and increase performance by up to 5.09 BLEU points on MWE test sets. We also devise a MWE score to specifically assess the quality of MWE translation which agrees with human evaluation. We make available the MWE score implementation – along with MWE-annotated training sets and corpus-based lists of MWEs – for reproduction and extension.</abstract>
<identifier type="citekey">zaninello-birch-2020-multiword</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.471</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3816</start>
<end>3825</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multiword Expression aware Neural Machine Translation
%A Zaninello, Andrea
%A Birch, Alexandra
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F zaninello-birch-2020-multiword
%X Multiword Expressions (MWEs) are a frequently occurring phenomenon found in all natural languages that is of great importance to linguistic theory, natural language processing applications, and machine translation systems. Neural Machine Translation (NMT) architectures do not handle these expressions well and previous studies have rarely addressed MWEs in this framework. In this work, we show that annotation and data augmentation, using external linguistic resources, can improve both translation of MWEs that occur in the source, and the generation of MWEs on the target, and increase performance by up to 5.09 BLEU points on MWE test sets. We also devise a MWE score to specifically assess the quality of MWE translation which agrees with human evaluation. We make available the MWE score implementation – along with MWE-annotated training sets and corpus-based lists of MWEs – for reproduction and extension.
%U https://aclanthology.org/2020.lrec-1.471
%P 3816-3825
Markdown (Informal)
[Multiword Expression aware Neural Machine Translation](https://aclanthology.org/2020.lrec-1.471) (Zaninello & Birch, LREC 2020)
ACL