Towards the interpretation of utterance sequences in a dialogue system

Authors:
Ingrid Zukerman;Patrick Ye;Kapil Kumar Gupta;Enes Makalic
Affiliations:
Monash University, Clayton, Victoria, Australia;Monash University, Clayton, Victoria, Australia;Monash University, Clayton, Victoria, Australia;Monash University, Clayton, Victoria, Australia
Venue:
SIGDIAL '09 Proceedings of the SIGDIAL 2009 Conference: The 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Year:
2009

Citing 9
Cited 0

Conceptual structures: information processing in mind and machine

Conceptual structures: information processing in mind and machine
An algorithm for pronominal anaphora resolution

Computational Linguistics
Information state and dialogue management in the TRINDI dialogue move engine toolkit

Natural Language Engineering
Corpus-based discourse understanding in spoken dialogue systems

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Probabilistic grounding of situated speech using plan recognition and reference resolution

ICMI '05 Proceedings of the 7th international conference on Multimodal interfaces
The SAMMIE system: multimodal in-car dialogue

COLING-ACL '06 Proceedings of the COLING/ACL on Interactive presentation sessions
Incremental natural language processing for HRI

Proceedings of the ACM/IEEE international conference on Human-robot interaction
Spontaneous speech understanding for robust multi-modal human-robot communication

COLING-ACL '06 Proceedings of the COLING/ACL on Main conference poster sessions
A machine learning approach to identification and resolution of one-anaphora

IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a probabilistic mechanism for the interpretation of sentence sequences developed for a spoken dialogue system mounted on a robotic agent. The mechanism receives as input a sequence of sentences, and produces an interpretation which integrates the interpretations of individual sentences. For our evaluation, we collected a corpus of hypothetical requests to a robot. Our mechanism exhibits good performance for sentence pairs, but requires further improvements for sentence sequences.