Document Inquisitor: un système de validation des structures et d'élicitation de modèles de documents.
Florian EvéquozMaurizio RigamontiDenis LalanneRolf IngoldPublished in: CIDE (2006)
Keyphrases
- document collections
- relevant documents
- document classification
- web documents
- document clustering
- information retrieval systems
- text documents
- document processing
- document content
- electronic documents
- information retrieval
- digital documents
- semi structured documents
- retrieval systems
- document retrieval
- document representation
- document analysis
- structured documents
- document ranking
- document type
- document similarity
- document structure
- document repository
- vector space model
- document set
- scientific documents
- multimedia documents
- keywords
- textual content
- retrieved documents
- latent semantic analysis
- xml format
- document summarization
- unstructured documents
- similar documents
- document images
- document archives
- index terms
- printed documents
- query terms
- topic hierarchy
- xml documents
- digital libraries
- retrieval strategies
- term frequency
- document centric
- ranked list
- document relevance
- document space
- pdf documents
- metadata
- related documents
- textual documents
- test collection
- automatic summarization
- query biased
- scanned documents
- query expansion
- latent topics
- keyword extraction
- user queries
- tf idf
- information extraction
- pdf files
- semantic information
- text collections
- training documents
- multi document summarization
- logical structure
- text summarization
- text classifiers
- topic models
- document level
- cross references
- co occurrence
- ieee trans