Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback.
Khanh NguyenHal Daumé IIIJordan L. Boyd-GraberPublished in: CoRR (2017)
Keyphrases
- machine translation
- reinforcement learning
- natural language processing
- language independent
- cross lingual
- information extraction
- statistical machine translation
- human subjects
- sensory inputs
- target language
- cross language information retrieval
- word sense disambiguation
- language processing
- natural language generation
- natural language
- chinese english
- language resources
- machine translation system
- brazilian portuguese
- word level
- word alignment
- query translation
- state space
- transfer learning
- dynamic programming
- machine learning
- question answering
- markov chain
- source language
- tasks in natural language processing