Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation.
Samuel KiegelandJulia KreutzerPublished in: NAACL-HLT (2021)
Keyphrases
- machine translation
- reinforcement learning
- natural language processing
- language independent
- cross lingual
- language processing
- cross language information retrieval
- statistical machine translation
- information extraction
- natural language generation
- target language
- markov decision processes
- parallel corpora
- natural language
- machine translation system
- word alignment
- language resources
- word sense disambiguation
- state space
- brazilian portuguese
- chinese english
- learning algorithm
- tasks in natural language processing
- multilingual documents
- optimal policy
- artificial intelligence