AN EVALUATION OF STRATEGIES FOR SELECTIVELY VERIFYING UTTERANCE MEANINGS IN SPOKEN NATURAL-LANGUAGE DIALOG

As with human-human interaction, spoken human-computer dialog will con tain situations where there is miscommunication. One natural strategy for reducing the impact of miscommunication is selective verification of the user utterance meanings. This paper reports on both context-ind ependent and context-dependent strategies for utterance verification t hat show that the use of dialog context can be very helpful in selecti ng which utterances to verify. Simulations with data collected during experimental trials with the Circuit Fix-It Shop spoken natural langua ge dialog system are used in the analysis. In addition, the performanc e of various selection strategies is measured separately for computer- controlled and user-controlled dialogs and general guidelines for sele cting an appropriate strategy are presented. (C) 1998 Academic Press L imited.