Unsupervised Tokenization for Machine Translation.
Tagyoung ChungDaniel GildeaPublished in: EMNLP (2009)
Keyphrases
- machine translation
- pos tagging
- natural language processing
- information extraction
- cross lingual
- language independent
- natural language
- cross language information retrieval
- named entities
- language processing
- statistical machine translation
- grammar induction
- target language
- natural language generation
- semi supervised
- lexical semantics
- unsupervised learning
- chinese english
- machine translation system
- parallel corpora
- query translation
- language specific
- statistical translation models
- tasks in natural language processing
- multilingual documents
- language resources
- word level
- source language
- question answering
- precision and recall
- information retrieval
- word sense disambiguation