Abstract
Foundation language models learn from their finetuning input context in different ways. In this paper, we reformulate inputs during finetuning for challenging translation tasks, leveraging model strengths from pretraining in novel ways to improve downstream performance. These reformulations are simple data level modifications, require no additional collection of training data or modification of data at inference time. They can be applied either on single language pair translation tasks or massively multilingual translation tasks. Experiments with these techniques demonstrate significant performance improvements up to 3.5 chrF++ on the Flores200 translation benchmark. We hope our research accessibly improves finetuning data efficiency, enabling more effective training to scalably improve state-of-the-art performance. Our code is released here.- Anthology ID:
- 2023.emnlp-main.638
- 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:
- 10322–10334
- Language:
- URL:
- https://preview.aclanthology.org/icon-24-ingestion/2023.emnlp-main.638/
- DOI:
- 10.18653/v1/2023.emnlp-main.638
- Cite (ACL):
- Brian Yu, Hansen Lillemark, and Kurt Keutzer. 2023. Simple and Effective Input Reformulations for Translation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 10322–10334, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Simple and Effective Input Reformulations for Translation (Yu et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/icon-24-ingestion/2023.emnlp-main.638.pdf