A plan recognition model for subdialogues in conversations

TLDR

Existing plan‑based dialogue models fail to capture many subdialogues because they do not distinguish the multiple ways utterances relate to topic plan structures. The paper proposes a plan‑based theory that permits a wide variety of utterance‑plan relationships. The authors define discourse plans that map specific utterance–topic relations and integrate discourse knowledge into a plan‑based framework, enabling modeling of diverse subdialogues while preserving computational efficiency. The resulting approach successfully models a wide range of subdialogues and retains the computational benefits of plan‑based systems.

Abstract

Previous plan-based models of dialogue understanding have been unable to account for many types of subdialogues present in naturally occurring conversations. One reason for this is that the models have not clearly differentiated between the varoius ways that an utterance can relate to a plan structure representing a topic. In this paper we present a plan-based theory that allows a wide variety of utterance-plan relationships. We introduce a set of discourse plans, each one corresponding to a particular way that an utterance can relate to a discourse topic, and distinguish such plans from the set of plans that are actually used to model the topics. By incorporating knowledge about discourse into a plan-based framework, we can account for a wide variety of subdialogues while maintaining the computational advantages of the plan-based approach.