Edwin Cortez

The hybrid application of an inductive learning method and a neural network for intelligent information retrieval

Abstract Traditional information retrieval systems based on Boolean logic suffer from two inherent problems: (1) inaccurate or incomplete query representation, and (2) inconsistent indexing. While many researchers have demonstrated that neural networks can solve the incomplete query problems for information retrieval, the inconsistent indexing problem still remains unsolved. In this paper, we present a hybrid methodology of integrating an inductive learning technique with a neural network (connectionist model) in order to solve both inconsistent indexing and incomplete query problems. Since an inductive learning technique has the ability to identify the most significant document index terms with various levels of relationship to their semantic significance, it provides a possible solution to the problem of inconsistent indexing. This paper reports the first phase of research that demonstrates how a neural network augmented by an inductive learning technique results in effective information retrieval performance in the areas that demand flexible inferencing and reasoning when incomplete queries and inconsistent indexing problems are present.

What the Library and Information Professional Can Learn from the Information Technology and Project Management Knowledge Areas

There are various forces driving change in the knowledge and skills areas for information professionals: 1) technologies, 2) changing environments, and 3) the changing role of information technology management. These forces affect all levels of information technology-based professionals--those responsible for information processing and those responsible for information services. This paper discusses and reviews the pertinent literature that deals with the competencies needed of information technology (IT) professionals, covering both general and project management knowledge and skills. Discussion follows relating this review to the library and information studies (LIS) field. The analysis leads to a composite picture, presented in a classification framework, of the competencies and skills needed of the new LIS professional.

Use of metadata vocabularies in data retrieval

Researchers have developed a prototype of a system that uses metadata to guide the user in selecting document databases of interest. A standardized vocabulary is used to index the document sets and is also used to locate databases. Once a database is located, then free-form searches are aided by the metadata vocabulary to locate specific documents. This system, the Research, Education, Economic Information System (REEIS), is being developed for the USDA to provide a way to locate programs, projects, and research that focus on food, agriculture, natural resources, and rural development.

Research, Education, and Economics Information System: An Engine for Strategic Planning and Information Policy Development at the U.S. Department of Agriculture.

Abstract This article describes the implementation of a strategic information audit as a key component in the development of the Research, Education, and Economics Information System (REEIS) at the U. S. Department of Agriculture (USDA). As a planning tool the audit is also viewed as an opportunity to bring into alignment the strategic intent of the four mission agencies with the use of state-of-the-art information technologies. Included in the article is a discussion of the systems model for researching organizational theory. The discussion and description is limited to phase one of a two-phase long-range project at the USDA.