Modelling Expectation in the Self-Repair Processing of Annotat-, um, Listeners

Abstract

This paper describes a statistical corpus study of self-repairs in the disfluency- annotated Switchboard corpus which examines the time-linear nature of self-repair processing for annotators and listeners in dialogue. The study suggests a strictly lo- cal detection and processing mechanism for self-repairs is sufficient, an advantage currently not used effectively under the bonnet of state-of-the-art automatic dis- fluency processing. We then show how simple local fluency measures using mod- ified language models can be strongly indicative of repair onset detection, and how simple information theoretic mea- sures could characterize different classes of repair