Improved Machine Translation Performance via Parallel Sentence Extraction from Comparable Corpora.
Dragos Stefan MunteanuAlexander M. FraserDaniel MarcuPublished in: HLT-NAACL (2004)
Keyphrases
- machine translation
- comparable corpora
- cross language information retrieval
- parallel corpora
- bilingual lexicon
- cross lingual
- information extraction
- language independent
- query translation
- natural language processing
- statistical machine translation
- machine translation system
- bilingual dictionaries
- word sense disambiguation
- news articles
- target language
- text corpora
- translation model
- parallel corpus
- language modeling
- language model
- word alignment
- data mining