CAREER: Intelligent Argument Generation in Text and Information Graphics

University Of North Carolina Greensboro, Greensboro NC

Investigators

Abstract

This is a Faculty Early Career Development (CAREER) award. The research will develop techniques for computer systems to communicate technical arguments to people without technical training, using integrated text and data graphics. It will integrate empirical methods from computational linguistics and human-computer interaction. Empirical methods will be used to determine appropriate techniques for conveying technical arguments to people with non-technical backgrounds. Initially, the project will develop analytical methods based on a corpus of human-authored multimedia presentations. For example, corpus studies can determine which features of arguments suggest where supporting graphics should be placed. Next, human-computer interaction experiments will be used to determine the effectiveness of techniques based on the analytical models, and to investigate alternatives to the techniques that are shown not to be sufficient. The resulting empirically-based techniques will be incorporated into computational models that will extend current approaches in natural language generation, automated graphic design, and intelligent multimedia presentation systems. The computational models will be demonstrated with a prototype system for genetic counseling. The educational component of this project will include new course curriculum, provide undergraduate and graduate computer science students with the opportunity to participate in research, and develop a laboratory for human-computer interaction studies that will be a resource for students and other faculty members. This CAREER award recognizes and supports the early career-development activities of a teacher-scholar who is likely to become an academic leader of the twenty-first century. Her research seeks solutions for the problem that people who lack appropriate technical training are faced with increasing responsibility for making vital decisions based on technical arguments, often involving quantitative and statistical data. If successful in the area of genetic counseling, the approach could be applied to many other areas where decision makers need help in using technical information and analyses.