A Compact Architecture for Dialogue Management Based on Scripts and Meta-Outputs

TL;DR

This paper presents a compact dialogue management architecture that transforms speech into executable scripts using successive linguistic and knowledge-based representations, enabling effective handling of diverse dialogue tasks.

Contribution

It introduces a novel architecture that combines outputs and meta-outputs for improved dialogue management and task handling in spoken interfaces.

Findings

Effective resolution of pronouns and misconceptions

Flexible handling of diverse dialogue tasks

Generation of executable scripts from speech signals

Abstract

We describe an architecture for spoken dialogue interfaces to semi-autonomous systems that transforms speech signals through successive representations of linguistic, dialogue, and domain knowledge. Each step produces an output, and a meta-output describing the transformation, with an executable program in a simple scripting language as the final result. The output/meta-output distinction permits perspicuous treatment of diverse tasks such as resolving pronouns, correcting user misconceptions, and optimizing scripts.