Abstract
Cross-lingual transfer has become an effective way of transferring knowledge between languages. In this paper, we explore an often overlooked aspect in this domain: the influence of the source language of a language model on language transfer performance. We consider a case where the target language and its script are not part of the pre-trained model. We conduct a series of experiments on monolingual and multilingual models that are pre-trained on different tokenization methods to determine factors that affect cross-lingual transfer to a new language with a unique script. Our findings reveal the importance of the tokenizer as a stronger factor than the shared script, language similarity, and model size.- Anthology ID:
- 2024.naacl-srw.14
- Volume:
- Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
- Month:
- June
- Year:
- 2024
- Address:
- Mexico City, Mexico
- Editors:
- Yang (Trista) Cao, Isabel Papadimitriou, Anaelia Ovalle, Marcos Zampieri, Francis Ferraro, Swabha Swayamdipta
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 124–129
- Language:
- URL:
- https://aclanthology.org/2024.naacl-srw.14
- DOI:
- 10.18653/v1/2024.naacl-srw.14
- Cite (ACL):
- Wondimagegnhue Tufa, Ilia Markov, and Piek Vossen. 2024. Unknown Script: Impact of Script on Cross-Lingual Transfer. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), pages 124–129, Mexico City, Mexico. Association for Computational Linguistics.
- Cite (Informal):
- Unknown Script: Impact of Script on Cross-Lingual Transfer (Tufa et al., NAACL 2024)
- PDF:
- https://preview.aclanthology.org/landing_page/2024.naacl-srw.14.pdf