To Translate or Not to Translate: A Systematic Investigation of Translation-Based Cross-Lingual Transfer to Low-Resource Languages

Benedikt Ebing, Goran Glavaš


Abstract
Perfect machine translation (MT) would render cross-lingual transfer (XLT) by means of multilingual language models (mLMs) superfluous. Given, on the one hand, the large body of work on improving XLT with mLMs and, on the other hand, recent advances in massively multilingual MT, in this work, we systematically evaluate existing and propose new translation-based XLT approaches for transfer to low-resource languages. We show that all translation-based approaches dramatically outperform zero-shot XLT with mLMs—with the combination of round-trip translation of the source-language training data and the translation of the target-language test instances at inference—being generally the most effective. We next show that one can obtain further empirical gains by adding reliable translations to other high-resource languages to the training data. Moreover, we propose an effective translation-based XLT strategy even for languages not supported by the MT system. Finally, we show that model selection for XLT based on target-language validation data obtained with MT outperforms model selection based on the source-language data. We believe our findings warrant a broader inclusion of more robust translation-based baselines in XLT research.
Anthology ID:
2024.naacl-long.298
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5325–5344
Language:
URL:
https://aclanthology.org/2024.naacl-long.298
DOI:
Bibkey:
Cite (ACL):
Benedikt Ebing and Goran Glavaš. 2024. To Translate or Not to Translate: A Systematic Investigation of Translation-Based Cross-Lingual Transfer to Low-Resource Languages. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 5325–5344, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
To Translate or Not to Translate: A Systematic Investigation of Translation-Based Cross-Lingual Transfer to Low-Resource Languages (Ebing & Glavaš, NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.298.pdf
Copyright:
 2024.naacl-long.298.copyright.pdf