Dr. Rau's research addresses the question of how computer systems can automatically construct and use representations of knowledge about what they know. This is important not only for extending our understanding of human behavior, but for increasing the intelligence, functionality, usability and efficiency of current- day computer systems. The objectives are to develop methods of extracting, representing and utilizing meta-knowledge automatically derived from text. Previous research has developed methods of extracting information from text, and methods of calculating the conceptual salience and breadth of knowledge from databases. This research will leverage these advances to develop novel methods of creating summary representations of the content of text, and demonstrate their applicability to the problem of increased accuracy and efficiency of conceptual information retrieval. The research methodology employed is experimental computer science. Working programs will implement algorithms that create meta- knowledge from text, and demonstrate advances by exhibiting new functionality with real problems in information access and retrieval. Interactive activities at the host institution include: hosting a two-day workshop on Diversity Awareness; teaching a graduate level course; putting together a program to provide educational and career opportunities for women; and holding a series of special seminars on "Industrial Research: What's it Like?" This project furthers VPW program objectives which are (1) to provide opportunities for women to advance their careers in engineering and in the disciplines of science supported by NSF and (2) to encourage women to pursue careers in science and engineering by providing greater visibility for women scientists and engineers employed in industry, government, and academic institutions. By encouraging the participation of women in science, it is a valuable investment in the Nation's future scientific vitality.
