Mining Parallel Resources for Machine Translation from Comparable Corpora.
Santanu PalPartha PakrayAlexander F. GelbukhJosef van GenabithPublished in: CICLing (1) (2015)
Keyphrases
- machine translation
- parallel corpora
- comparable corpora
- cross language information retrieval
- language independent
- cross lingual
- bilingual lexicon
- machine translation system
- statistical machine translation
- linguistic resources
- natural language processing
- target language
- data mining
- information extraction
- query translation
- bilingual dictionaries
- text mining
- word pairs
- knowledge discovery
- word alignment
- statistical translation models
- cross language
- error prone
- natural language
- information retrieval
- machine learning