Multi-domain machine translation enhancements by parallel data extraction from comparable corpora.
Krzysztof WolkEmilia RejmundKrzysztof MarasekPublished in: CoRR (2016)
Keyphrases
- machine translation
- comparable corpora
- cross language information retrieval
- parallel corpora
- bilingual lexicon
- cross lingual
- information extraction
- semi structured
- natural language processing
- target language
- language independent
- query translation
- statistical machine translation
- language modeling
- news articles
- bilingual dictionaries
- natural language
- translation model
- cross domain
- data analysis
- machine translation system
- cross language
- image retrieval
- word alignment
- parallel corpus
- linguistic resources
- feature selection