Abstract
k-nearest-neighbor machine translation has demonstrated remarkable improvements in machine translation quality by creating a datastore of cached examples. However, these improvements have been limited to high-resource language pairs, with large datastores, and remain a challenge for low-resource languages. In this paper, we address this issue by combining representations from multiple languages into a single datastore. Our results consistently demonstrate substantial improvements not only in low-resource translation quality (up to +3.6 BLEU), but also for high-resource translation quality (up to +0.5 BLEU). Our experiments show that it is possible to create multilingual datastores that are a quarter of the size, achieving a 5.3x speed improvement, by using linguistic similarities for datastore creation.- Anthology ID:
- 2023.emnlp-main.571
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 9200–9208
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.571
- DOI:
- 10.18653/v1/2023.emnlp-main.571
- Cite (ACL):
- David Stap and Christof Monz. 2023. Multilingual k-Nearest-Neighbor Machine Translation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9200–9208, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Multilingual k-Nearest-Neighbor Machine Translation (Stap & Monz, EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2023.emnlp-main.571.pdf