Abstract
Recent work has shown that, while large language models (LLMs) demonstrate strong word translation or bilingual lexicon induction (BLI) capabilities in few-shot setups, they still cannot match the performance of ‘traditional’ mapping-based approaches in the unsupervised scenario where no seed translation pairs are available, especially for lower-resource languages. To address this challenge with LLMs, we propose self-augmented in-context learning (SAIL) for unsupervised BLI: starting from a zero-shot prompt, SAIL iteratively induces a set of high-confidence word translation pairs for in-context learning (ICL) from an LLM, which it then reapplies to the same LLM in the ICL fashion. Our method shows substantial gains over zero-shot prompting of LLMs on two established BLI benchmarks spanning a wide range of language pairs, also outperforming mapping-based baselines across the board. In addition to achieving state-of-the-art unsupervised BLI performance, we also conduct comprehensive analyses on SAIL and discuss its limitations.- Anthology ID:
- 2024.acl-short.67
- Volume:
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short 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:
- 743–753
- Language:
- URL:
- https://aclanthology.org/2024.acl-short.67
- DOI:
- Cite (ACL):
- Yaoyiran Li, Anna Korhonen, and Ivan Vulić. 2024. Self-Augmented In-Context Learning for Unsupervised Word Translation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 743–753, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- Self-Augmented In-Context Learning for Unsupervised Word Translation (Li et al., ACL 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.acl-short.67.pdf