Integrating Multiple Knowledge Sources for Detection and Correction of Repairs in Human-Computer Dialog

We have analyzed 607 sentences of spontaneous human-computer speech data containing repairs, drawn from a total corpus of 10,718 sentences. We present here 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… CONTINUE READING

8 Figures & Tables

Topics

Statistics

01020'95'98'01'04'07'10'13'16
Citations per Year

157 Citations

Semantic Scholar estimates that this publication has 157 citations based on the available data.

See our FAQ for additional information.