Automatic Evaluation and Analysis of Idioms in Neural Machine Translation

Christos Baziotis, Prashant Mathur, Eva Hasler


Abstract
A major open problem in neural machine translation (NMT) is the translation of idiomatic expressions, such as “under the weather”. The meaning of these expressions is not composed by the meaning of their constituent words, and NMT models tend to translate them literally (i.e., word-by-word), which leads to confusing and nonsensical translations. Research on idioms in NMT is limited and obstructed by the absence of automatic methods for quantifying these errors. In this work, first, we propose a novel metric for automatically measuring the frequency of literal translation errors without human involvement. Equipped with this metric, we present controlled translation experiments with models trained in different conditions (with/without the test-set idioms) and across a wide range of (global and targeted) metrics and test sets. We explore the role of monolingual pretraining and find that it yields substantial targeted improvements, even without observing any translation examples of the test-set idioms. In our analysis, we probe the role of idiom context. We find that the randomly initialized models are more local or “myopic” as they are relatively unaffected by variations of the idiom context, unlike the pretrained ones.
Anthology ID:
2023.eacl-main.267
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3682–3700
Language:
URL:
https://aclanthology.org/2023.eacl-main.267
DOI:
10.18653/v1/2023.eacl-main.267
Bibkey:
Cite (ACL):
Christos Baziotis, Prashant Mathur, and Eva Hasler. 2023. Automatic Evaluation and Analysis of Idioms in Neural Machine Translation. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 3682–3700, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Automatic Evaluation and Analysis of Idioms in Neural Machine Translation (Baziotis et al., EACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.eacl-main.267.pdf
Video:
 https://aclanthology.org/2023.eacl-main.267.mp4