Characterizing indirect speech acts
Computational Linguistics
Indirect speech acts: characterizing multiple forms
ACM SIGART Bulletin
Failure handling in a dialogue system
IJCAI'77 Proceedings of the 5th international joint conference on Artificial intelligence - Volume 1
| Hi-index | 0.00 |
This report describes a framework for handling mixed-initiative English dialogue in a console session environment, with emphasis on recognition. Within this framework, both linguistic and non-linguistic activities are modeled by structures called methods. which are a declarative form of procedural knowledge. Our design focuses on units of linguistic activity larger than the speech act, so that the pragmatic and semantic context of an utterance can be used to guide its interpretation. Also important is the treatment of indirect speech acts, e.g., the different ways to ask a question, give a command, etc. Given the static model of dialogue embodied in the methods, the problem is to find the correct method step that relates to a particular input. We handle this problem through a combination of careful structural distinctions and the use of multiple recognition strategies. The dialogue methods are used to generate expectations dynamically, special structures are used to facilitate matching, and a basic distinction between four major utterance classes is used to determine which of several overall matching strategies should be used for a given expectation.