Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback
Authors:
- Khanh NguyenKNKhanh Nguyen
- Hal Daumé IiiHIHal Daumé Iii
- Jordan Boyd-GraberJBJordan Boyd-Graber
Open Access
- 1 January 2017
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 1464-1474