Learning to interpret utterances using dialogue history

Authors:
David DeVault;Matthew Stone
Affiliations:
University of Southern California, Marina del Rey, CA;Rutgers University, Piscataway, NJ
Venue:
EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics
Year:
2009

Citing 13
Cited 4

Interpretation as abduction

Artificial Intelligence - Special volume on natural language processing
A maximum entropy approach to natural language processing

Computational Linguistics
Combining labeled and unlabeled data with co-training

COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
Toward natural language interfaces for robotic agents: grounding linguistic meaning in sensors

AGENTS '00 Proceedings of the fourth international conference on Autonomous agents
The agreement process: an empirical investigation of human—human computer-mediated collaborative dialogs

International Journal of Human-Computer Studies - Special issue on collaboration, cooperation and conflict in dialogue systems
Contentful mental states for robot baby

Eighteenth national conference on Artificial intelligence
A corpus-based investigation of definite description use

Computational Linguistics
A multimodal learning interface for grounding spoken language in sensory perceptions

ACM Transactions on Applied Perception (TAP)
Partially observable Markov decision processes for spoken dialog systems

Computer Speech and Language
Modeling the impact of shared visual information on collaborative reference

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Learning n-best correction models from implicit user feedback in a multi-modal local search application

SIGdial '08 Proceedings of the 9th SIGdial Workshop on Discourse and Dialogue
Learning content selection rules for generating object descriptions in dialogue

Journal of Artificial Intelligence Research
Contribution tracking: participating in task-oriented dialogue under uncertainty

Contribution tracking: participating in task-oriented dialogue under uncertainty

On designing task-oriented intelligent interfaces: an e-mail based design framework

ICIC'10 Proceedings of the Advanced intelligent computing theories and applications, and 6th international conference on Intelligent computing
Learning to balance grounding rationales for dialogue systems

SIGDIAL '11 Proceedings of the SIGDIAL 2011 Conference
Corpus evidence for preference-driven interpretation

AC'11 Proceedings of the 18th Amsterdam colloquim conference on Logic, Language and Meaning
Knowledge acquisition through human---robot multimodal interaction

Intelligent Service Robotics

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe a methodology for learning a disambiguation model for deep pragmatic interpretations in the context of situated task-oriented dialogue. The system accumulates training examples for ambiguity resolution by tracking the fates of alternative interpretations across dialogue, including subsequent clarificatory episodes initiated by the system itself. We illustrate with a case study building maximum entropy models over abductive interpretations in a referential communication task. The resulting model correctly resolves 81% of ambiguities left unresolved by an initial handcrafted baseline. A key innovation is that our method draws exclusively on a system's own skills and experience and requires no human annotation.