Food for Thought: How can we exploit contextual embeddings in the translation of idiomatic expressions?

Lukas Santing, Ryan Sijstermans, Giacomo Anerdi, Pedro Jeuris, Marijn ten Thij, Riza Batista-Navarro


Abstract
Idiomatic expressions (or idioms) are phrases where the meaning of the phrase cannot be determined from the meaning of the individual words in the expression. Translating idioms between languages is therefore a challenging task. Transformer models based on contextual embeddings have advanced the state-of-the-art across many domains in the field of natural language processing. While research using transformers has advanced both idiom detection as well as idiom disambiguation, idiom translation has not seen a similar advancement. In this work, we investigate two approaches to fine-tuning a pretrained Text-to-Text Transfer Transformer (T5) model to perform idiom translation from English to German. The first approach directly translates English idiom-containing sentences to German, while the second is underpinned by idiom paraphrasing, firstly paraphrasing English idiomatic expressions to their simplified English versions before translating them to German. Results of our evaluation show that each of the approaches is able to generate adequate translations.
Anthology ID:
2022.flp-1.14
Volume:
Proceedings of the 3rd Workshop on Figurative Language Processing (FLP)
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates (Hybrid)
Editors:
Debanjan Ghosh, Beata Beigman Klebanov, Smaranda Muresan, Anna Feldman, Soujanya Poria, Tuhin Chakrabarty
Venue:
Fig-Lang
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
100–110
Language:
URL:
https://aclanthology.org/2022.flp-1.14
DOI:
10.18653/v1/2022.flp-1.14
Bibkey:
Cite (ACL):
Lukas Santing, Ryan Sijstermans, Giacomo Anerdi, Pedro Jeuris, Marijn ten Thij, and Riza Batista-Navarro. 2022. Food for Thought: How can we exploit contextual embeddings in the translation of idiomatic expressions?. In Proceedings of the 3rd Workshop on Figurative Language Processing (FLP), pages 100–110, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
Cite (Informal):
Food for Thought: How can we exploit contextual embeddings in the translation of idiomatic expressions? (Santing et al., Fig-Lang 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.flp-1.14.pdf
Video:
 https://aclanthology.org/2022.flp-1.14.mp4