A computational theory of grounding in natural language conversation
A computational theory of grounding in natural language conversation
Plan Recognition in Natural Language Dialogue
Plan Recognition in Natural Language Dialogue
Context Representation for Dialogue Management
CONTEXT '99 Proceedings of the Second International and Interdisciplinary Conference on Modeling and Using Context
The TRAINS Project: A Case Study in Defining a Conversational Planning Agent
The TRAINS Project: A Case Study in Defining a Conversational Planning Agent
The independence of dimensions in multidimensional dialogue act annotation
NAACL-Short '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers
Multidimensional dialogue management
SigDIAL '06 Proceedings of the 7th SIGdial Workshop on Discourse and Dialogue
Towards a multidimensional semantics of discourse markers in spoken dialogue
IWCS-8 '09 Proceedings of the Eighth International Conference on Computational Semantics
Multifunctionality in dialogue
Computer Speech and Language
The semantics of dialogue acts
IWCS '11 Proceedings of the Ninth International Conference on Computational Semantics
| Hi-index | 0.00 |
This paper presents a context-based approach to the analysis and computational modeling of communicative behaviour in dialogue. This approach, known as Dynamic Interpretation Theory (DIT), claims that dialogue behaviour is multifunctional, i.e. functional segments of speech and nonverbal behaviour have more than one communicative function. A 10-dimensional taxonomy of communicative functions has been developed, which has been applied successfully by human annotators and by computer programs in the analysis of spoken and multimodal dialogue; which can be used for the functional markup of ECA behaviour; and which forms the basis of an ISO standard for dialogue act annotation. An analysis of the types of information involved in each of the dimensions leads to a design of compartmented, 'multidimensional' context models, which have been used for multimodal dialogue management and in a computational model of grounding.