Emora STDM: A Versatile Framework for Innovative Dialogue System Development

TL;DR

Emora STDM is a flexible dialogue system framework that enables rapid prototyping and collaborative development of complex chat-based interactions, supporting diverse expertise levels and integrating multiple management approaches.

Contribution

The paper introduces Emora STDM, a versatile framework combining state machine and information state approaches for dialogue management, with seamless NLP integration and a user-friendly workflow.

Findings

Students with varied backgrounds successfully developed dialogue managers quickly.

The framework improved efficiency in creating complex dialogue interactions.

User study demonstrated broad applicability and ease of use.

Abstract

This demo paper presents Emora STDM (State Transition Dialogue Manager), a dialogue system development framework that provides novel workflows for rapid prototyping of chat-based dialogue managers as well as collaborative development of complex interactions. Our framework caters to a wide range of expertise levels by supporting interoperability between two popular approaches, state machine and information state, to dialogue management. Our Natural Language Expression package allows seamless integration of pattern matching, custom NLP modules, and database querying, that makes the workflows much more efficient. As a user study, we adopt this framework to an interdisciplinary undergraduate course where students with both technical and non-technical backgrounds are able to develop creative dialogue managers in a short period of time.