Towards Topic Driven Access to Full Text Documents.
Caterina CaraccioloWillem Robert van HageMaarten de RijkePublished in: ECDL (2004)
Keyphrases
- information retrieval systems
- journal articles
- expert finding
- retrieval systems
- document set
- topic modeling
- document collections
- document content
- information retrieval
- topic segmentation
- topic specific
- legal information
- multi document summarization
- access control
- topic hierarchy
- relevant documents
- topic discovery
- news stories
- digital libraries
- related documents
- textual content
- web documents
- focused crawling
- concept space
- latent topics
- plain text
- query topic
- metadata
- document retrieval
- document classification
- cd roms
- topic detection
- query biased
- latent dirichlet allocation
- vector space
- automatic summarization
- query expansion
- word frequency
- statistical topic models
- document summaries
- keywords
- focused crawler
- web search
- topic models
- semantic information
- related topics
- text mining
- text analysis
- text documents
- free text
- user interests
- vector space model