Multi-reward Based Reinforcement Learning for Neural Machine Translation.
Shuo SunHongxu HouNier WuZiyue GuoChaowei ZhangPublished in: CNCL (2020)
Keyphrases
- machine translation
- reinforcement learning
- natural language processing
- language independent
- cross lingual
- language processing
- cross language information retrieval
- information extraction
- target language
- natural language generation
- state space
- word alignment
- markov decision processes
- word sense disambiguation
- language resources
- optimal policy
- statistical machine translation
- multilingual documents
- brazilian portuguese
- learning algorithm
- machine translation system
- natural language
- dynamic programming
- machine transliteration
- machine learning
- statistical translation models
- markov chain
- source language
- information retrieval systems