Ryan Fellows^1*, Hisham Ihshaish¹, Steve Battle¹, Ciaran Haines¹, Peter Mayhew^1,2, J.Ignacio Deza^{1, 3}, ¹University of the West of England (UWE), United Kingdom, ²GE Aviation, Cheltenham, United Kingdom, ³Universidad Atlántida Argentina, Argentina

Task-oriented dialogue systems (TODS) – designed to assist users to achieve a goal – 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 have not yet reached 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, are usually ignored. This can harm the interactions between the human and the dialogue system leaving the user dissatisfied or frustrated. This paper explores the role of conversational quality attributes within dialogue systems, looking at if, how, and where they are utilised, and examining their correlation with the performance of the dialogue system.

Dialogue Systems, Chatbot, Conversational Agents, AI, Natural Language Processing, Quality Attributes.