Exploiting multilingual nomenclatures and language-independent text features as an interlingua for cross-lingual text analysis applications
Ralf SteinbergerBruno PouliquenCamelia IgnatPublished in: CoRR (2006)
Keyphrases
- cross lingual
- language independent
- text analysis
- machine translation
- multi lingual
- information extraction
- natural language processing
- language specific
- cross language
- text mining
- text retrieval
- text documents
- language modeling
- text classification
- n gram
- monolingual and cross lingual
- machine translation system
- parallel corpora
- parallel corpus
- news articles
- machine learning
- cross language information retrieval
- feature space
- natural language
- document clustering
- word segmentation
- text corpora
- text categorization
- language model
- document retrieval
- bag of words
- word sense
- bayesian networks
- information retrieval