Filtering or adapting: two strategies to exploit noisy parallel corpora for cross-language information retrieval.
Lixin ShiJian-Yun NiePublished in: CIKM (2006)
Keyphrases
- cross language information retrieval
- parallel corpora
- comparable corpora
- english chinese
- machine translation
- query translation
- parallel texts
- bilingual dictionaries
- cross language
- out of vocabulary
- language independent
- language resources
- translation model
- query terms
- cross lingual
- machine translation system
- statistical machine translation
- labor intensive
- sentence level
- information retrieval
- fully automated
- natural language processing
- information extraction