Using plans to understand natural language
Robert Wilensky · 1976
Our ability to build a natural language understanding system is limited by the degree to which we can organize and apply world knowledge. This paper describes a program, called PAM, that has knowledge about people's intentions. PAM uses its knowledge to infer the relationships between sentences in a text. A sample run of the program is presented and is described in detail. The inference mechanisms of PAM are compared to those of other knowledge-application programs.