Detection and Correction of Repairs in Human-Computer Dialog
SRI INTERNATIONAL MENLO PARK CA
Pagination or Media Count:
The authors have analyzed 607 sentences of spontaneous human-computer speech data containing repairs that were drawn from a total corpus of 10,718 sentences. In this paper, they present criteria and techniques for automatically detecting the presence of a repair, its location, and making the appropriate correction. The criteria involve integration of knowledge from several sources pattern matching, syntactic and semantic analysis, and acoustics. In summary, disfluencies occur at high enough rates in human-computer dialog to merit consideration. In contrast to earlier approaches, the authors have made it their goal to detect and correct repairs automatically, without assuming an explicit edit signal. Without such an edit signal, however, repairs are easily confused both with false positives and with other repairs. Preliminary results show that pattern matching is effective at detecting repairs without excessive overgeneration. Their syntacticsemantic approaches are quite accurate at detecting repairs and correcting them. Acoustics is a third source of information that can be tapped to provide evidence about the existence of a repair. While none of these knowledge sources by itself is sufficient, they propose that by combining them, and possibly others, one can greatly enhance ones ability to detect and correct repairs. As a next step, they intend to explore additional aspects of the syntax and semantics of repairs, analyze further acoustic patterns, and pursue the question of how best to integrate information from these multiple knowledge sources.
- Human Factors Engineering and Man Machine Systems
- Voice Communications