Task-oriented Dialogue Systems: performance vs. quality-optima, a review
It addresses the problem of user frustration in dialogue systems for industries using them, but is incremental as it reviews existing literature.
This paper reviews task-oriented dialogue systems, examining how focusing on task-resolution metrics may neglect conversational quality attributes, which can lead to user dissatisfaction, and explores the correlation between these attributes and system performance.
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.