Multi-document summarization by visualizing topical content
Rie Kubota Ando, Branimir Boguraev, Roy J. Byrd et al. · 2000
This paper describes a framework for multi-document summarization which combines three premises: coherent themes can be identified reliably; highly representative themes, running across subsets of the document collection, can function as multi-document summary surrogates; and effective end-use of such themes should be facilitated by a visualization environment which clarifies the relationship between themes and documents. We present algorithms that formalize our framework, describe an implementation, and demonstrate a prototype system and interface.
Cited by 39 works. doi:10.3115/1117575.1117584 Open-access PDF
Authors
References
- Indexing by latent semantic analysis
- Introduction to Modern Information Retrieval
- Visualizing the non-visual: spatial analysis and interaction with information from text documents
- Generating Natural Language Summaries from Multiple On-Line Sources
- Information fusion in the context of multi-document summarization
- The TIPSTER SUMMAC Text Summarization Evaluation
- Summarizing Similarities and Differences Among Related Documents
- The Architecture of the Festival Speech Synthesis System
- Self-organizing maps of document collections: A new approach to interactive exploration
- Visualization of a document collection: The vibe system