Discussion of text summarization in information-retrieval systems focuses on summarizing the similarities and differences in information content among documents. Highlights a tool for analyzing document collections such as multiple news stories about an event or sequence of events. Contains 58 references. (Author/LRW)

Discusses indexing methods in Korean text retrieval and proposes a new indexing method based on n-grams which can handle compound nouns effectively without dictionaries and complex linguistic knowledge. Experimental results show that n-gram-based indexing is considerably faster than morpheme-based indexing, and also provides better retrieval…

Summarizes a prototype geographical image retrieval system that demonstrates how to integrate image processing and information analysis techniques to support large-scale content-based image retrieval. Describes an experiment to validate the performance of this image retrieval system against that of human subjects by examining similarity analysis…

Introduces a conceptual integration approach to heterogeneous databases or information systems that exploits the similarity in metalevel information and performs metadata mining on database objects to discover a set of concepts that serve as a domain abstraction and provide a conceptual layer above existing legacy systems. Presents results of…

Discusses the distinction between record-oriented and pattern-oriented questions and relates them to information seeking at museums. Describes the Core of Discovery, a prototype system for exploring collections of textual data at The Historic New Orleans Collection, which includes keyword retrieval, concept retrieval, and pattern-oriented…

Discusses the logical approach to information retrieval that treats retrieval as inference, considers probabilistic models for text retrieval, and presents an approach for combining Datalog (a variant of Horn predicate logic) with probabilistic theory using intentional semantics with logical rules. Discusses syntax and semantics and compares this…

Presents a new model for combining multiple sources of evidence in database merging based on logistic regression, and occurring only when ranks are available as a key to be used to merge different ranked lists obtained by various retrieval schemes. Results indicate better retrieval effectiveness than other approaches. (LRW)

Discusses the requirements of information retrieval systems to support creative thinking as well as more convergent thinking. Highlights include the nature of creative thinking; similarity relationships; serendipity; machine processing of similarities; high order knowledge representation; and fuzzy and parallel information retrieval. (Contains 34…

A study of 24 scientific articles in the South African Computer Journal compared four term-weighting schemes for detecting information-rich passages in texts. Results demonstrated that word categories and frequency-derived weights were closely correlated but that weighting according to first mention theory (cue-method) and frequency-based weights…

Discussion of the study of interactive information retrieval (IR) at the Text Retrieval Conferences (TREC) focuses on summaries of the Interactive Track at each conference. Describes evolution of the track, which has changed from comparing human-machine systems with fully automatic systems to comparing interactive systems that focus on the search…

Compares a user-defined passage feedback system to a document feedback system for information retrieval, based on TREC (Text Retrieval Conference) guidelines. Highlights include a description of IRIS, an interactive retrieval system; text processing; ranking; term weights; feedback models, including the adaptive linear model; and suggestions for…

Provides directions for developing search strategies to be used on the World Wide Web and with gopher on the Internet. (JOW)

Summarizes a presentation that discussed findings and implications of research projects using an Internet search service and Internet-accessible vendor databases, representing the two sides of public database searching: query formulation and resource utilization. Presenters included: Tefko Saracevic, Amanda Spink, Dietmar Wolfram and Hong Xie.…

Presents an abstract for a planned session on historical perspectives on encyclopedism, from 17th century initiatives to modern thought. Presentations include: "Concepts of Encyclopedia and the Organisation and Retrieval of Knowledge: Historical Perspectives" (W. Boyd Rayward); "Encyclopedism at the End of Modernity" (Mikel…

Discusses the growing gap between what is available on the Internet and what search engines can retrieve, particularly data lost in the breach of the unindexable, versus the unindexed, Web. Highlights include products designed to focus on content that is usually missed by search engines; and directories versus search engines. (Contains 10…