DiBiMT: A Novel Benchmark for Measuring Word Sense Disambiguation Biases in Machine Translation

Niccolò Campolungo, Federico Martelli, Francesco Saina, Roberto Navigli


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.
Anthology ID:
2022.acl-long.298
Original:
2022.acl-long.298v1
Version 2:
2022.acl-long.298v2
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4331–4352
Language:
URL:
https://aclanthology.org/2022.acl-long.298
DOI:
10.18653/v1/2022.acl-long.298
Award:
 Best Resource Paper
Bibkey:
Cite (ACL):
Niccolò Campolungo, Federico Martelli, Francesco Saina, and Roberto Navigli. 2022. DiBiMT: A Novel Benchmark for Measuring Word Sense Disambiguation Biases in Machine Translation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4331–4352, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
DiBiMT: A Novel Benchmark for Measuring Word Sense Disambiguation Biases in Machine Translation (Campolungo et al., ACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/2022.acl-long.298.pdf