Improved syntactic models for parsing speech with repairs

Abstract:

This paper introduces three new syntactic models for representing speech with repairs. These models are developed to test the intuition that the erroneous parts of speech repairs (reparanda) are not generated or recognized as such while occurring, but only after they have been corrected. Thus, they are designed to minimize the differences in grammar rule applications between fluent and disfluent speech containing similar structure. The three models considered in this paper are also designed to isolate the mechanism of impact, by systematically exploring different variables.