Exploiting Variant Corpora for Machine Translation.
Michael PaulEiichiro SumitaPublished in: HLT-NAACL (2006)
Keyphrases
- machine translation
- natural language processing
- chinese english
- statistical machine translation
- parallel corpora
- parallel corpus
- machine readable dictionaries
- cross language information retrieval
- comparable corpora
- cross lingual
- language independent
- natural language
- language processing
- information extraction
- target language
- word sense disambiguation
- machine translation system
- word alignment
- language resources
- linguistic resources
- natural language generation
- wordnet
- training corpus
- bilingual lexicon
- machine learning
- tasks in natural language processing