MultiX : un formalisme pour l'encodage des documents multi-structurés.
Noureddine ChattiSylvie CalabrettoPublished in: INFORSID (2006)
Keyphrases
- machine learning
- document collections
- information retrieval
- document retrieval
- information retrieval systems
- document content
- relevant documents
- metadata
- web documents
- textual content
- xml documents
- user queries
- logical structure
- multi document summarization
- multimedia documents
- index terms
- ranked list
- document classification
- vector space model
- highly relevant
- retrieved documents
- data sets
- time stamped
- text mining
- text analysis
- topic modeling
- semantic relationships
- document representation
- text retrieval
- document clustering
- vector space
- text documents
- website
- language model