Abductive reasoning for continual dialogue understanding

Authors:
Miroslav Janíček
Affiliations:
German Research Center for Artificial Intelligence (DFKI), Saarbrücken, Germany
Venue:
ESSLLI'10 Proceedings of the 2010 international conference on New Directions in Logic, Language and Computation
Year:
2010

Citing 8
Cited 0

Temporal ontology and temporal reference

Computational Linguistics - Special issue on tense and aspect
Intention is choice with commitment

Artificial Intelligence
Interpretation as abduction

Artificial Intelligence - Special volume on natural language processing
Probabilistic Horn abduction and Bayesian networks

Artificial Intelligence
Artificial Intelligence: A Modern Approach

Artificial Intelligence: A Modern Approach
Coupling CCG and hybrid logic dependency semantics

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Continual planning and acting in dynamic multiagent environments

Autonomous Agents and Multi-Agent Systems
Probabilistic semantics for cost based abduction

AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present a continual context-sensitive abductive framework for understanding situated spoken natural dialogue. The framework builds up and refines a set of partial defeasible explanations of the spoken input, trying to infer the speaker's intention. These partial explanations are conditioned on the eventual verification of the knowledge gaps they contain. This verification is done by executing test actions, thereby going beyond the initial context. The approach is illustrated by an example set in the context of human-robot interaction.