@inproceedings{raganato-etal-2020-evaluation,
title = "An Evaluation Benchmark for Testing the Word Sense Disambiguation Capabilities of Machine Translation Systems",
author = {Raganato, Alessandro and
Scherrer, Yves and
Tiedemann, J{\"o}rg},
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-1.452",
pages = "3668--3675",
abstract = "Lexical ambiguity is one of the many challenging linguistic phenomena involved in translation, i.e., translating an ambiguous word with its correct sense. In this respect, previous work has shown that the translation quality of neural machine translation systems can be improved by explicitly modeling the senses of ambiguous words. Recently, several evaluation test sets have been proposed to measure the word sense disambiguation (WSD) capability of machine translation systems. However, to date, these evaluation test sets do not include any training data that would provide a fair setup measuring the sense distributions present within the training data itself. In this paper, we present an evaluation benchmark on WSD for machine translation for 10 language pairs, comprising training data with known sense distributions. Our approach for the construction of the benchmark builds upon the wide-coverage multilingual sense inventory of BabelNet, the multilingual neural parsing pipeline TurkuNLP, and the OPUS collection of translated texts from the web. The test suite is available at \url{http://github.com/Helsinki-NLP/MuCoW}.",
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="raganato-etal-2020-evaluation">
<titleInfo>
<title>An Evaluation Benchmark for Testing the Word Sense Disambiguation Capabilities of Machine Translation Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Raganato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</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>Lexical ambiguity is one of the many challenging linguistic phenomena involved in translation, i.e., translating an ambiguous word with its correct sense. In this respect, previous work has shown that the translation quality of neural machine translation systems can be improved by explicitly modeling the senses of ambiguous words. Recently, several evaluation test sets have been proposed to measure the word sense disambiguation (WSD) capability of machine translation systems. However, to date, these evaluation test sets do not include any training data that would provide a fair setup measuring the sense distributions present within the training data itself. In this paper, we present an evaluation benchmark on WSD for machine translation for 10 language pairs, comprising training data with known sense distributions. Our approach for the construction of the benchmark builds upon the wide-coverage multilingual sense inventory of BabelNet, the multilingual neural parsing pipeline TurkuNLP, and the OPUS collection of translated texts from the web. The test suite is available at http://github.com/Helsinki-NLP/MuCoW.</abstract>
<identifier type="citekey">raganato-etal-2020-evaluation</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.452</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3668</start>
<end>3675</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Evaluation Benchmark for Testing the Word Sense Disambiguation Capabilities of Machine Translation Systems
%A Raganato, Alessandro
%A Scherrer, Yves
%A Tiedemann, Jörg
%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 raganato-etal-2020-evaluation
%X Lexical ambiguity is one of the many challenging linguistic phenomena involved in translation, i.e., translating an ambiguous word with its correct sense. In this respect, previous work has shown that the translation quality of neural machine translation systems can be improved by explicitly modeling the senses of ambiguous words. Recently, several evaluation test sets have been proposed to measure the word sense disambiguation (WSD) capability of machine translation systems. However, to date, these evaluation test sets do not include any training data that would provide a fair setup measuring the sense distributions present within the training data itself. In this paper, we present an evaluation benchmark on WSD for machine translation for 10 language pairs, comprising training data with known sense distributions. Our approach for the construction of the benchmark builds upon the wide-coverage multilingual sense inventory of BabelNet, the multilingual neural parsing pipeline TurkuNLP, and the OPUS collection of translated texts from the web. The test suite is available at http://github.com/Helsinki-NLP/MuCoW.
%U https://aclanthology.org/2020.lrec-1.452
%P 3668-3675
Markdown (Informal)
[An Evaluation Benchmark for Testing the Word Sense Disambiguation Capabilities of Machine Translation Systems](https://aclanthology.org/2020.lrec-1.452) (Raganato et al., LREC 2020)
ACL