Considers the role of human intellectual indexing in the face of increasingly sophisticated automatic indexing techniques. Critiques the comparative research and explores the nature of human analysis of messages or texts and efforts to formulate rules to make human practice more predictable. (Author/LRW)

Examines the knowledge base of an intermediary expert system that provides advice about search term selection. Topics include a proposal for an integrated approach, including an option focusing on terminological attributes based on knowledge acquired from professional searchers; and the content of the knowledge base and the research needed to…

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…

Discusses the need to index foreign words for information retrieval that are used in Korean text and presents an effective foreign word recognition and extraction method based on word segmentation. Uses both unknown word information acquired through the automatic dictionary compilation and foreign word recognition information. (Author/LRW)

Report on exploratory research which investigated image attributes in a series of describing tasks. Results suggest that access to a wide range of attributes is needed to address all facets of interest and that certain classes of attributes may appear more frequently (literal objects, human form and associated attributes, color, and location).…

Discusses the inclusion of contextual information in indexing and retrieval systems to improve results and the ability to carry out text analysis by means of linguistic knowledge. Presents research that investigated whether discourse variables have an impact on information and retrieval and classification algorithms. (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…

Reports on the progress of the natural language information retrieval project, a joint effort led by GE (General Electric) Research, and its evaluation at the sixth TREC (Text Retrieval Conference). Discusses stream-based information retrieval, which uses alternative methods of document indexing; advanced linguistic streams; weighting; and query…

Discusses statistical word indexing for Japanese information-retrieval systems and proposes a new method that uses statistics about characters to evaluate a bi-gram's likelihood of being a word boundary. Describes a new segmentation strategy that extracts some overlapping segments and results in higher retrieval effectiveness. (Author/LRW)

Discusses the role of search engines in Web usability and analyzes and evaluates the retrieval effectiveness of various indexing and searching strategies on a new Web text collection. Highlights include preprocessing techniques that might improve retrieval effectiveness; and hyperlinks as useful sources of evidence in improving retrieval…

Proposes a fuzzy-image database model and a concept of fuzzy space; describes fuzzy-query processing in fuzzy space and fuzzy indexing on complete fuzzy vectors; and uses an example image database, the computer-aided facial-image inference and retrieval system (CAFIIR), for explanation throughout. (Author/LRW)

Describes WebClass, a system that allows Web users to create personalized conceptual data that is dynamically merged with original HTML source by a proxy server. Explains the creation of alternative views of Web pages, data modeling, and navigation; and describes two possible applications of the system, annotation and indexing. (Author/LRW)

Considers the need for keyphrase-extraction techniques in intelligent Chinese information retrieval and presents a PAT-tree-based adaptive approach, developed from the PATRICIA Algorithm (Practical Algorithm to Retrieve Information Coded in Alphanumeric). Discusses Internet utilization, automatic term suggestion, domain-specific lexicon…

Discusses latent semantic indexing (LSI); considers the high cost associated with the singular value decomposition (SVD) of the large term-by-document matrix that becomes a barrier for its application to scalable information retrieval; and shows that information filtering using level search techniques can reduce the SVD computation cost for LSI.…

Discussion of multimedia libraries and the need for storage, indexing, and retrieval techniques focuses on the combination of computer vision and data mining techniques to model high-level concepts for image retrieval based on perceptual features of the human visual system. Uses fuzzy set theory to measure users' assessments and to capture users'…