Abstract
Every person speaks or writes their own flavor of their native language, influenced by a number of factors: the content they tend to talk about, their gender, their social status, or their geographical origin. When attempting to perform Machine Translation (MT), these variations have a significant effect on how the system should perform translation, but this is not captured well by standard one-size-fits-all models. In this paper, we propose a simple and parameter-efficient adaptation technique that only requires adapting the bias of the output softmax to each particular user of the MT system, either directly or through a factored approximation. Experiments on TED talks in three languages demonstrate improvements in translation accuracy, and better reflection of speaker traits in the target text.- Anthology ID:
- P18-2050
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 312–318
- Language:
- URL:
- https://aclanthology.org/P18-2050
- DOI:
- 10.18653/v1/P18-2050
- Cite (ACL):
- Paul Michel and Graham Neubig. 2018. Extreme Adaptation for Personalized Neural Machine Translation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 312–318, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Extreme Adaptation for Personalized Neural Machine Translation (Michel & Neubig, ACL 2018)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/P18-2050.pdf
- Code
- neulab/extreme-adaptation-for-personalized-translation