Discussion of access methods and information retrieval algorithms focuses on the vertical counting approach. Determines the speedup gained from using the Hamming Distance Bit Vertical counter, evaluates the parameters that influence the speedup, and discusses the point that makes the vertical approach faster than the horizontal approach.…

Discusses the problem of enhancing the speed of Huffman decoding of compressed data. Topics addressed include the Huffman decoding tree; multibit decoding; binary string mapping problems; and algorithms for solving mapping problems. (22 references) (LRW)

Describes a system for the automatic coding of most descriptive titles which generates Nested Phrase Indexing System (NEPHIS) input strings of sufficient quality for permuted index production. A series of examples and an 11-item reference list accompany the text. (JL)

Describes system design proposed by the Spelling Error Detection Correction Project (SPEEDCOP) at Chemical Abstracts Service. Highlights include principles of detection/correction system; spelling error detection (the dictionary, suffix normalization, bypassing specialized word classes, document-level frequency threshold); spelling error…

Presents an approach to a Genetic Information Retrieval Agent Filter (GIRAF) that filters and ranks documents retrieved from the Internet according to users' preferences by using a Genetic Algorithm and fuzzy set theory to handle the imprecision of users' preferences and users' evaluation of the retrieved documents. (Author/LRW)

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…

Discussion of models for information retrieval focuses on an application of linear algebra to text clustering, namely, a metric for measuring cluster quality based on the theory that cluster quality is proportional to the number of terms that are disjoint across the clusters. Explains term-document matrices and clustering algorithms. (Author/LRW)

Discussion of the failure of individual keywords to identify conceptual content of documents in retrieval systems highlights Metric Similarity Modeling, a method for creating vector space representation of documents based on modeling target interdocument similarity values. Semantic relatedness, latent semantic indexing, an indexing and retrieval…

Investigates methods for the correct and efficient handling of annotations in a full-text information-retrieval system in a hypertext environment. Goals were to increase relevant items retrieved, reduce non-relevant items, permit selective retrieval, and to explore the notion of distance between words as given in the distance-evaluation algorithm.…

Discussion of electronic news available on the World Wide Web focuses on a methodology of associating news documents using similarity measures and a name-phrase algorithm to create news representations that can be compared and ranked to find related news items. Considers precision over recall and interactivity with the users. (Author/LRW)

Describes a bottom-up procedure for discovering multivalued dependencies in observed data without knowing a priori the relationships among the attributes. The proposed algorithm is an application of technique designed for learning conditional independencies in probabilistic reasoning; a prototype system for automated database schema design has…

Describes SWEAR (Systematic Weighting and Ranking), a powers-of-two algorithm that can be used for searching the World Wide Web or any large database that automatically creates discrete, well-defined result sets and displays them in decreasing order of likely relevance. Also discusses fuzzy sets. (Author/LRW)

Presents a heuristic, attribute-based, noise-tolerant data mining program, HCV (Version 2.0) based on the newly-developed extension matrix approach. Outlines some techniques implemented in the HCV program for noise handling and discretization of continuous domains; an empirical comparison shows that rules generated by HCV are more compact than the…

Evaluates the effectiveness of spelling-correction and string-similarity matching methods in retrieving similar words in a Malay dictionary associated with a set of query words. Describes experiments that showed the best search combination used a stemming algorithm, and calculates retrieval effectiveness and relevant means measures from weighted…

Discussion of language barriers when using multilingual digital library collections on the Internet focuses on query translation and document translation in a Chinese-English information retrieval system called MTIR. Highlights include a bilingual dictionary; machine transliteration algorithm; design issues for document translation; HTML tags; and…