Paper Info
Title
On the use of expectations for detecting and repairing human-machine miscommunication
Abstract
In this paper I describe how miscommunication problems are dealt with in the spoken language system DIALOGOS. The dialogue module of the system exploits dialogic expectations in a twofold way: to model what future user utterance might be about (predictions), and to account how the user's next utterance may be related to previ- ous ones in the ongoing interaction (pragmatic- based expectations). The analysis starts from the hypothesis that the occurrence of miscommuni- cation is concomitant with two pragmatic phe- nomena: the deviation of the user from the ex- pected behaviour and the generation of a conver- sational implicature. A preliminary evaluation of a large amount of interactions between subjects and DIALOGOS shows that the system perfor- mance is enhanced by the uses of both predictions and pragmatic-based expectations. The problem During the last few years it has been emerging that the success of spoken language systems is greatly im- proved by the contextual reasoning of dialogue mod- ules. This tenet has spread through both the speech and the dialogue communities. Dialogue systems devoted to spoken language applications are able to detect partial communication breakdowns by other system modules, and that increases the robustness of human-machine in- teractions by speech. During oral interactions with computers, communica- tion problems often arise after the occurrence of errors during the recognition phase. Sometimes these errors cannot be solved by the semantic module: the utter- ances containing them are interpreted by the seman- tic analyser, but with an information content different from the speaker's intended meaning. Detecting such miscommunications and repairing them through initial- ization of appropriate repair subdialogues is essential for the interaction to be successful. Most of the research in this area has been devoted to providing the recognition and understanding modules
Year
Venue
Keywords
1997
Computing Research Repository
information content
DocType
Volume
Citations 
Journal
cmp-lg/971
11
PageRank 
References 
Authors
1.27
6
2
Name
Order
Citations
PageRank
Morena Danieli116132.23
Reiss Romoli2111.27