Task-oriented Dialogue Systems: performance vs. quality-optima, a review

TL;DR

This review analyzes how task-oriented dialogue systems balance task success with conversational quality, highlighting gaps in evaluation metrics and their impact on user satisfaction.

Contribution

It provides a comprehensive overview of evaluative frameworks and explores the relationship between dialogue quality attributes and system performance.

Findings

Current systems prioritize task completion over conversational quality.

Evaluation metrics often overlook user satisfaction and dialogue naturalness.

There is a need for integrated metrics combining task success and quality attributes.

Abstract

Task-oriented dialogue systems (TODS) are continuing to rise in popularity as various industries find ways to effectively harness their capabilities, saving both time and money. However, even state-of-the-art TODS are not yet reaching their full potential. TODS typically have a primary design focus on completing the task at hand, so the metric of task-resolution should take priority. Other conversational quality attributes that may point to the success, or otherwise, of the dialogue, may be ignored. This can cause interactions between human and dialogue system that leave the user dissatisfied or frustrated. This paper explores the literature on evaluative frameworks of dialogue systems and the role of conversational quality attributes in dialogue systems, looking at if, how, and where they are utilised, and examining their correlation with the performance of the dialogue system.