This two-part article combines a comprehensive account of a probabilistic model of retrieval with new systematic experiments on TREC (Text Retrieval Conferences) Program material. Part 1 covers the foundations and the model development for document collection and relevance data, along with the test apparatus. Data and results tables for both parts…

Evaluates the performance of different methods of data compression coding in several situations. Huffman's code, arithmetic coding, fixed codes, fast approximations to arithmetic coding, and splay coding are discussed in terms of their speed, memory requirements, and proximity to optimal performance. Recommendations for the best methods of…

Describes a series of user studies used to advance understanding of how people use electronic tables (E-tables) and inform the development of a Web-based statistical table browser for use by non-specialists. Results of needs assessment, prototype development, and user studies provide a foundation for understanding E-tables in general and guiding…

Presents a technique for dividing text into field-coherent passages based upon extracting field-associated words or phrases from the text by determining how topics grow, shrink and shift from sentence to sentence. Proposes measures of topic continuity and transition and suggests how those may be used to find the passage boundaries. (Author/LRW)

Describes an approximate document ranking process that uses a compact array of in-memory, low-precision approximations for document length. Combined with another rule for reducing the memory required by partial similarity accumulators, the approximation heuristic allows the ranking of large document collections using less than one byte of memory…

Discusses hierarchic document clustering in information retrieval and its potential improved effectiveness over inverted file search (IFS). Describes experiments conducted to determine whether hierarchic clustering can increase the retrieval effectiveness compared to both static clustering and of conventional IFS when it is applied to search…

Discusses information retrieval system design that supports various information-seeking strategies. Describes a study that investigated the relationship between users' information-seeking goals and their information-seeking behavior to specify hierarchical levels of user goals, and discusses results that focus on patterns of interactive intentions…

Presents a relevance-feedback strategy that improves the effectiveness of information-retrieval systems based on back-propagation of the relevance of retrieved documents using an algorithm developed in a neural approach. Describes a neural information-retrieval model and reports results obtained with the algorithm in three different environments.…

Discussion of image database systems focuses on semantic queries and shows how an image is abstracted into a hierarchy of entity names and features; how relations are established between entities visible in the image; and how a "fuzzy" matching technique is used to compare semantic queries to image abstractions. (Author/LRW)

Describes experiments in the retrieval of spoken documents in multimedia systems. Problems in spoken document retrieval are discussed, and a voice mail application is explained that combines state-of-the-art speech recognition with established document retrieval technologies to provide an effective and efficient retrieval tool. (Author/LRW)

Describes a study that investigated document retrieval relevance based on document length in an experimental text collection. Topics include term weighting and document ranking, retrieval strategies such as the vector-space cosine match, and a modified technique called the pivoted cosine normalization. (LRW)

Describes a detailed algorithm for fast text compression. Related to the PPM (prediction by partial matching) method, it simplifies the modeling phase by eliminating the escape mechanism and speeds up coding by using a combination of quasi-arithmetic coding and Rice coding. Details of the use of quasi-arithmetic code tables are given, and their…

Analyzes relevance assessments of topical descriptors for bibliographic records for two dimensions: (1) a vertical conceptual hierarchy of broad to narrow descriptors, and (2) a horizontal linkage of related terms. The data were analyzed for a semantic distance and semantic direction effect as postulated by the Semantic Distance Model. (Author/LRW)

Discussion of MEDLINE document indexing focuses on a study that assessed the use of free text, Medical Subject Headings (MeSH), and a variety of combination retrieval strategies. Prior research involving free text and controlled vocabularies is reviewed, and results of the study indicate that MeSH does have an important role in text retrieval.…

Describes a study that examined the effectiveness of eight search engines for the World Wide Web. Calculated traditional information-retrieval measures of recall and precision at varying numbers of retrieved documents to use as the bases for statistical comparisons of retrieval effectiveness. Also examined the overlap between search engines.…