Abstract
In this paper, we introduce UniBridge (Cross-Lingual Transfer Learning with Optimized Embeddings and Vocabulary), a comprehensive approach developed to improve the effectiveness of Cross-Lingual Transfer Learning, particularly in languages with limited resources. Our approach tackles two essential elements of a language model: the initialization of embeddings and the optimal vocabulary size. Specifically, we propose a novel embedding initialization method that leverages both lexical and semantic alignment for a language. In addition, we present a method for systematically searching for the optimal vocabulary size, ensuring a balance between model complexity and linguistic coverage. Our experiments across multilingual datasets show that our approach greatly improves the F1-Score in several languages. UniBridge is a robust and adaptable solution for cross-lingual systems in various languages, highlighting the significance of initializing embeddings and choosing the right vocabulary size in cross-lingual environments.- Anthology ID:
- 2024.acl-long.174
- Volume:
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3168–3184
- Language:
- URL:
- https://aclanthology.org/2024.acl-long.174
- DOI:
- 10.18653/v1/2024.acl-long.174
- Cite (ACL):
- Trinh Pham, Khoi Le, and Anh Tuan Luu. 2024. UniBridge: A Unified Approach to Cross-Lingual Transfer Learning for Low-Resource Languages. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3168–3184, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- UniBridge: A Unified Approach to Cross-Lingual Transfer Learning for Low-Resource Languages (Pham et al., ACL 2024)
- PDF:
- https://preview.aclanthology.org/add_acl24_videos/2024.acl-long.174.pdf