Towards a Principled Representation of Discourse Plans
R. Michael Young (Intelligent Systems Program, University of, Pittsburgh), Johanna D. Moore (Department of Computer Science, Learning, Research, Development Center, University of Pittsburgh), Martha E., Pollack (Department of Computer Science, Intelligent Systems Program,
TL;DR
This paper introduces DPOCL, a planning algorithm that constructs discourse plans capturing causal and decompositional relations, improving dialogue participation and addressing issues in previous discourse planners.
Contribution
The paper presents DPOCL, a novel planning algorithm that effectively models discourse relations, enhancing dialogue systems' flexibility and coherence.
Findings
DPOCL successfully models causal and decompositional discourse relations.
The new plan structures improve dialogue system performance.
The approach addresses limitations of previous discourse planners.
Abstract
We argue that discourse plans must capture the intended causal and decompositional relations between communicative actions. We present a planning algorithm, DPOCL, that builds plan structures that properly capture these relations, and show how these structures are used to solve the problems that plagued previous discourse planners, and allow a system to participate effectively and flexibly in an ongoing dialogue.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMulti-Agent Systems and Negotiation · Speech and dialogue systems · Natural Language Processing Techniques