Corpus-based cross-language information retrieval in retrieval of highly relevant documents.
Tuomas TalvensaariMartti JuholaJorma LaurikkalaKalervo JärvelinPublished in: J. Assoc. Inf. Sci. Technol. (2007)
Keyphrases
- cross language information retrieval
- highly relevant documents
- cross language retrieval
- query terms
- multilingual information retrieval
- query translation
- cross language
- relevant documents
- machine translation
- document retrieval
- query expansion
- information retrieval
- information retrieval systems
- highly relevant
- test collection
- parallel corpora
- document collections
- relevance assessments
- retrieval model
- language model
- text retrieval
- retrieval systems
- retrieval effectiveness
- database systems
- co occurrence
- user queries
- natural language processing
- text classification
- bilingual dictionaries
- relevance feedback
- metadata