Discusses the problems and current research techniques being explored in the area of Cross Language Information Retrieval (CLIR) for finding documents in languages other than the original query. Discusses language identification methods, techniques for automatically generating queries in other languages, and retrieving and merging query results.…

The study has applied speech recognition and text-mining technologies to a set of recorded outbound marketing calls and analyzed the results. Since speaker-independent speech recognition technology results in a significantly lower recognition rate than that found when the recognizer is trained for a particular speaker, a number of post-processing…

Presents an overview of feedback within the cybernetics and social frameworks. These feedback concepts are then compared with the interactive feedback concept evolving within the framework of information seeking and retrieving, based on their conceptualization of the feedback loop and notion of information. (Author/AEF)

Reports an approach to automatic thesaurus construction for Chinese documents. Presents an effective Chinese keyword extraction algorithm. Compared to previous studies, this method speeds up the thesaurus generation process drastically. It also achieves a similar percentage level of term relatedness. Includes three tables and four figures.…

Contends that large databases contain hidden knowledge, or literature that is logically linked but not bibliographically linked, that contains academically interesting commonalities not retrievable by normal searching methods. Based on search methods for discovering previously unknown causes of medical syndromes, a method for discovering new…

Categorizes different theoretical justifications of data fusion into two approaches, examines their implications, analyzes some unsuccessful data fusion experiments, and proposes two conditions for effective data fusion. Results indicate that the efficacy and inter-scheme dissimilarity are good predictors for effectiveness of data fusion.…

Zipf's law states that if words in a text are arranged in decreasing order of occurrence, then the product of the rank of a word and the number of times it occurs is a constant of that text. Examination of the probabilities of occurrence of multi-word phrases in information retrieval in relation to the probabilities of occurrence of single words…

Proposes a structure for natural language descriptions of the semantic content of visual materials that requires descriptions to be (modified) keywords, phrases, or simple sentences, with components that are grammatical relations common to many languages. This structure makes it easy to implement a collection's descriptions as a relational…

The purpose of the study was to determine how many questions judged relevant to an article are also judged relevant using different length representations of the article, and how this proportion changes as the length of the representation changes. Several persons made relevance judgments for each of a set of articles to each of a set of questions.…

Describes database and index design and data collection methods for compilation of the National Tune Index, a comprehensive, multifaceted tool for research in and analysis of eighteenth century American and British secular music, restoration of early American theater works, and identification of specific tune or text fragments. (MBR)

This paper considers the processing of digital library queries, consisting of a text component and a structured component in distributed environments. The paper concentrates on the processing of the structured component of a distributed query. A method is proposed to identify the databases that are likely to be useful for processing any given…

Judged by the criterion of practical relevance, the application of computers in the law is a subject which, over the past fifteen years, has promised much, but fulfilled little. (68 references) (Author)

Proposes a composite feature measure which combines the shape and color features of an image based on a clustering technique. A similarity measure computes the degree of match between a given pair of images; this technique can be used for content-based image retrieval of images using shape and/or color. Tests the technique on two image databases;…

An obvious and natural approach to organizing a large corpus of data is a hierarchical index--akin to a book's table of contents. The type of corpus dealt with here is a bibliographical repository, with entries form a limited domain. Given such an index, it is desirable that search results point to relevant locations in the hierarchy, rather than…

Addresses the query- versus document-oriented dichotomy in information retrieval. Introduces a maximum likelihood approach to utilizing feedback data that can be used to construct a concrete object function that estimates both document and query parameters in accordance with all available feedback data. (AEF)