This paper describes a method of detecting speechrepairs that uses a part-of-speech tagger. The tagger is given knowledgeabout category transitions for speechrepairs, and sois ableto mark a transition either as a likely repair or as fluent speech. Other contextual clues, such as editing terms, word fragments, and word matchings, are alsofactored in by modifying the transition probabilities.
Peter A. Heeman, James F. Allen