Describes research conducted at the TREC (Text Retrieval Conference) interactive track that compared Boolean and natural language searching, showing they achieved comparable results; and assessed the validity of batch-oriented retrieval evaluations, showing that the results from batch evaluations were not comparable to those obtained in…

Discussion of natural language processing focuses on a multi-strategic integrated text preprocessing method for difficult problems of sentence boundary disambiguation and word boundary disambiguation of Web texts. Describes an evaluation of the method using Korean Web document collections. (Author/LRW)

Describes a study that investigated the use of natural language questions on Web search engines. Highlights include query languages; differences in search engine syntax; and results of logistic regression and analysis of variance that showed aspects of questions that predicted significantly different performances, including the number of 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…

This work describes a framework that combines techniques from Adaptive Hypermedia and Natural Language processing in order to create, in a fully automated way, on-line information systems from linear texts in electronic format, such as textbooks. The process is divided into two steps: an "off-line" processing step, which analyses the source text,…

A National Initiative has been formed to address the urgent need for the humanities and arts to gain a voice in the planning and development of the National Information Infrastructure (NII). This report makes a case for the importance of connecting all people with electronic access to the nation's cultural heritage, and relates the special…

A museum can talk to its audience through a variety of channels, such as Web sites, help desks, human guides, brochures. A considerable effort is being made by museums to integrate these different means. The Web site can be designed to be reachable or even updateable from visitors inside the museum via touchscreen and wireless devices. But these…

Discusses the role of ontology in knowledge representation, including enabling content-based access, interoperability, communications, and new levels of service on the Semantic Web; reviews current ontology generation studies and projects as well as problems facing such research; and discusses ontology mapping, information extraction, natural…

Presents an approach to summarization that combines information from multiple facts into a single sentence using linguistic constructions. Describes two applications: one produces summaries of basketball games, and the other contains summaries of telephone network planning activity. Both summarize input data as opposed to full text. Discusses…

Discusses the development of phraseological machine translation based on the theory that in natural languages, phraseological units cannot always be reduced to words. Describes the phraseological translation process of computer software and machine dictionary systems that translate Russian into English and English into Russian. (JMV)

Natural language processing (NLP) is concerned with getting computers to do useful things with natural language. Major applications include machine translation, text generation, information retrieval, and natural language interfaces. Reviews important developments since 1987 that have led to advances in NLP; current NLP applications; and problems…

Five computerized role-playing scenarios accepting unrestricted natural language input were administered to 72 freshman medical students. The scenarios measured and automatically scored responses on five psychological dimensions: social skills, level of frustration, submissiveness, combativeness, and negotiative ability. Tests identified…

Presents three different statistical techniques for identifying content-bearing phrases within a natural language database. Describes results on the effectiveness of the scoring methods when applied to MEDLINE phrases, and how the three methods can be combined to improve performance. Processing results for an example document are provided.…

Explores the interrelation between Web publishing and information retrieval technologies and lists new approaches to Web indexing and searching. Highlights include Web directories; search engines; portalisation; Internet service providers; browser providers; meta search engines; popularity based analysis; natural language searching; links-based…

Boolean systems still constitute most of the installed base of online public access catalogues (OPACs) in the French universities even if many studies have shown that Boolean operators are not frequently used by non-librarian users (by contrast with professional librarians). The first study examined the use of Boolean operators by French…