ABSTRACT
Human speech is creative. Move specifically, it is an effortful process that starts from a rich input and creates new meaning. Speech is also incremental, as evidenced by pauses and false starts. Existing models of language generation have not adequately addressed these phenomena. This paper presents six principles which specify a design for a cognitively plausible generator, as follows: Be able to handle non-trivial inputs, Be able to access relevant words, Consider many words as candidates for potential inclusion, Produce an utterance incrementally, Use feedback from words, and Monitor the output. These principles can be implemented using spreading activation in a semantic network which includes lexical and syntactic knowledge. The prototype generation system FIG is such an implementation.
