A Flexible, Parallel Generator of Natural Language

My Ph.D. thesis (Ward 1992, 1991)1 addressed the task of generating natural language utterances. Current generators only accept input that are relatively poor in information, such as feature structures or lists of propositions; they are unable to deal with input rich in information, as one might expect from, for example, an expert system with a complete model of its domain or a natural language understander with good inference ability. FIG is based on a single associative network that encodes lexical knowledge, syntactic knowledge, and world knowledge. Thus, FIG is a spreading activation or structured connectionist system (Feldman et al.