Word normalization and decompounding in mono- and bilingual IR.
Eija AirioPublished in: Inf. Retr. (2006)
Keyphrases
- machine translation system
- cross language
- compound words
- text retrieval
- machine translation
- parallel corpus
- word alignment
- information retrieval
- english chinese
- parallel corpora
- bilingual lexicon
- spoken document retrieval
- language independent
- statistical machine translation
- multiword
- sentence pairs
- cross lingual
- term weighting
- query translation
- translation model
- cross language information retrieval
- n gram
- information access
- co occurrence
- question answering
- query expansion
- word pairs
- document retrieval
- source language
- word recognition
- information retrieval systems
- word level
- statistical translation models
- chinese english
- ad hoc information retrieval
- sparck jones
- bilingual dictionaries
- retrieval effectiveness
- test collection
- document collections
- language model
- term dependencies
- indian languages
- target language
- model for information retrieval
- term dependence
- blind relevance feedback
- relevance feedback
- information extraction