Discusses automatic thesaurus construction and characterizes the statistical behavior of terms by using an inference network. Highlights include low-frequency terms and data sparseness, Bayesian networks, collocation maps and term similarity, constructing a thesaurus from a collocation map, and experiments with test collections. (Author/LRW)

Presents entirely automatic methods for gathering documents for a hypertext, for linking the set, and for annotating those connections with a description of the type (that is, the nature) of the link. Document linking is based on information retrieval similarity measures with adjustable levels of strictness. Evaluation problems are also…

Discusses the use of information retrieval techniques for the automatic authoring of hypertext. Presents a typology of hypertext links, describes examples of automatic construction of hypertext, and considers evaluation problems. (LRW)

Discussion of the use of information retrieval techniques for automatic generation of semantic hypertext links focuses on automatic text summarization. Topics include World Wide Web links, text segmentation, and evaluation of text summarization by comparing automatically generated abstracts with manually prepared abstracts. (Author/LRW)

Describes a prototype system for software documentation management called SLEUTH (Software Literacy Enhancing Usefulness to Humans) being developed at the University of Virginia. Highlights include information retrieval techniques, hypertext links that are installed automatically, a WAIS (Wide Area Information Server) search engine, user…

Discusses access methods in hypermedia and information retrieval and describes a research project in which similarity measures have been extended to include imprecise matching over different dimensions of structured classification schemes. The semantic similarity of information units forms the basis for the automatic construction of links and is…

Discusses problems associated with manually created or maintained hyperdocument links and the need for automatic methods, describes a system for the automatic detection and management of various links, and presents a case study of a World Wide Web hyperbase for the Australian parliament. (Author/LRW)

Text similarity measurements are used to determine relationships between natural-language texts and text excerpts. The resulting linked hypertext maps can be broken down into text segments and themes used to identify different text types and structures, leading to improved information access and utilization. Examples are provided for text…

Reports an approach to interactive information seeking that is grounded in the idea of summarizing query results through automated document clustering. The authors' prototype acted as an intermediate layer between the user and a commercial Internet search engine. Data was processed from 36 users and it was concluded that the prototype improved…

Presents two methods for evaluating automatically generated hypertext links: one is based on correlations between shortest paths in the hypertext structure and a semantic similarity measure, and the other is based on measuring users' performances using hypertext. Advantages and disadvantages of computer versus human evaluation are discussed.…

The purpose of this research is to simulate the manual process of assigning descriptors to magazine articles by machine, to investigate how successful automated assignment of descriptors to a heterogeneous text collection is when a text classifier is trained based upon a small set of manually classified example texts, and to test performance of…

Describes the design and implementation of TACHIR, a tool for the automatic construction of hypertexts for information retrieval. Topics include a three-level conceptual model; navigating among documents, index terms, and concepts; the use of HTML (Hypertext Markup Language) and the World Wide Web; evaluation of TACHIR; and future possibilities.…

Discusses a method for organizing and augmenting the data in a complex database to make automatic retrieval possible. Presents an example of the method using a database of information on the nature and use of fungicides. Initial results of trials with potential users suggest that the system can produce relevant responses to queries. (Author/AEF)

Describes SALOMON (Summary and Analysis of Legal texts for Managing Online Needs), a system which automatically summarizes Belgian criminal cases to improve access to court decisions. Highlights include a text grammar represented as a semantic network; automatic abstracting; knowledge acquisition and representation; parsing; evaluation, including…