Editorial Comprehension in OpEd through Argument Units

Proceedings of the AAAI Conference on Artificial Intelligence, 5

Volume

Science

Cognitive Modeling and Education

This paper presents a theory of reasoning and argument comprehension currently implemented in OpEd, a computer system that reads short politico-economic editorials and answers questions about the editorial contents. We believe that all arguments are composed of a fixed number of abstract argument structures, which we call Argument Units (AUs). Thus, argument comprehension is viewed in OpEd fundamentally as the process of recognizing, instantiating, and applying argument units. Here we discuss: (a) the knowledge and processes necessary to understand opinions, arguments, and issues which arise in politico-economic editorials; and (b) the relation of this research to previous work in natural language understanding. A description of OpEd and examples of its current input/output behavior are also presented in this paper.