@inproceedings{campolungo-etal-2022-dibimt,
title = "{D}i{B}i{MT}: A Novel Benchmark for Measuring {W}ord {S}ense {D}isambiguation Biases in {M}achine {T}ranslation",
author = "Campolungo, Niccol{\`o} and
Martelli, Federico and
Saina, Francesco and
Navigli, Roberto",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.298",
doi = "10.18653/v1/2022.acl-long.298",
pages = "4331--4352",
abstract = "Lexical ambiguity poses one of the greatest challenges in the field of Machine Translation. Over the last few decades, multiple efforts have been undertaken to investigate incorrect translations caused by the polysemous nature of words. Within this body of research, some studies have posited that models pick up semantic biases existing in the training data, thus producing translation errors. In this paper, we present DiBiMT, the first entirely manually-curated evaluation benchmark which enables an extensive study of semantic biases in Machine Translation of nominal and verbal words in five different language combinations, namely, English and one or other of the following languages: Chinese, German, Italian, Russian and Spanish. Furthermore, we test state-of-the-art Machine Translation systems, both commercial and non-commercial ones, against our new test bed and provide a thorough statistical and linguistic analysis of the results. We release DiBiMT at \url{https://nlp.uniroma1.it/dibimt} as a closed benchmark with a public leaderboard.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="campolungo-etal-2022-dibimt">
<titleInfo>
<title>DiBiMT: A Novel Benchmark for Measuring Word Sense Disambiguation Biases in Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Niccolò</namePart>
<namePart type="family">Campolungo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Federico</namePart>
<namePart type="family">Martelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesco</namePart>
<namePart type="family">Saina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Lexical ambiguity poses one of the greatest challenges in the field of Machine Translation. Over the last few decades, multiple efforts have been undertaken to investigate incorrect translations caused by the polysemous nature of words. Within this body of research, some studies have posited that models pick up semantic biases existing in the training data, thus producing translation errors. In this paper, we present DiBiMT, the first entirely manually-curated evaluation benchmark which enables an extensive study of semantic biases in Machine Translation of nominal and verbal words in five different language combinations, namely, English and one or other of the following languages: Chinese, German, Italian, Russian and Spanish. Furthermore, we test state-of-the-art Machine Translation systems, both commercial and non-commercial ones, against our new test bed and provide a thorough statistical and linguistic analysis of the results. We release DiBiMT at https://nlp.uniroma1.it/dibimt as a closed benchmark with a public leaderboard.</abstract>
<identifier type="citekey">campolungo-etal-2022-dibimt</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.298</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.298</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>4331</start>
<end>4352</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DiBiMT: A Novel Benchmark for Measuring Word Sense Disambiguation Biases in Machine Translation
%A Campolungo, Niccolò
%A Martelli, Federico
%A Saina, Francesco
%A Navigli, Roberto
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F campolungo-etal-2022-dibimt
%X Lexical ambiguity poses one of the greatest challenges in the field of Machine Translation. Over the last few decades, multiple efforts have been undertaken to investigate incorrect translations caused by the polysemous nature of words. Within this body of research, some studies have posited that models pick up semantic biases existing in the training data, thus producing translation errors. In this paper, we present DiBiMT, the first entirely manually-curated evaluation benchmark which enables an extensive study of semantic biases in Machine Translation of nominal and verbal words in five different language combinations, namely, English and one or other of the following languages: Chinese, German, Italian, Russian and Spanish. Furthermore, we test state-of-the-art Machine Translation systems, both commercial and non-commercial ones, against our new test bed and provide a thorough statistical and linguistic analysis of the results. We release DiBiMT at https://nlp.uniroma1.it/dibimt as a closed benchmark with a public leaderboard.
%R 10.18653/v1/2022.acl-long.298
%U https://aclanthology.org/2022.acl-long.298
%U https://doi.org/10.18653/v1/2022.acl-long.298
%P 4331-4352
Markdown (Informal)
[DiBiMT: A Novel Benchmark for Measuring Word Sense Disambiguation Biases in Machine Translation](https://aclanthology.org/2022.acl-long.298) (Campolungo et al., ACL 2022)
ACL