Automatic Analysis, Theme Generation, and Summarization of Machine-Readable Texts
- 3 June 1994
- journal article
- research article
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 264 (5164) , 1421-1426
- https://doi.org/10.1126/science.264.5164.1421
Abstract
Vast amounts of text material are now available in machine-readable form for automatic processing. Here, approaches are outlined for manipulating and accessing texts in arbitrary subject areas in accordance with user needs. In particular, methods are given for determining text themes, traversing texts selectively, and extracting summary statements that reflect text content.Keywords
This publication has 15 references indexed in Scilit:
- Structural analysis of hypertextsACM Transactions on Information Systems, 1992
- Developments in Automatic Text RetrievalScience, 1991
- Global Text Matching for Information RetrievalScience, 1991
- Constructing literature abstracts by computer: Techniques and prospectsInformation Processing & Management, 1990
- Hypertext in literary education, criticism, and scholarshipComputers and the Humanities, 1989
- Generation and search of clustered filesACM Transactions on Database Systems, 1978
- Clustering large files of documents using the single‐link methodJournal of the American Society for Information Science, 1977
- Retrieval of answer-sentences and answer-figures from papers by text searchingInformation Processing & Management, 1975
- A vector space model for automatic indexingCommunications of the ACM, 1975
- Automatic abstracting and indexing—survey and recommendationsCommunications of the ACM, 1961