Task-oriented dialogue systems: Performance vs. quality-optima, a review

Fellows, Ryan; Ihshaish, Hisham; Battle, Steve; Haines, Ciaran; Mayhew, Peter; Deza, J Ignacio

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.

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 3rd International Conference on Natural Language Processing and Computational Linguistics (NLPCL 2022)
• Start Date: Jul 30, 2022
• End Date: Jul 31, 2022
• Acceptance Date: May 18, 2022
• Online Publication Date: Jul 31, 2022
• Publication Date: Jul 31, 2022
• Deposit Date: Jan 7, 2022
• Publicly Available Date: Sep 5, 2022
• Volume: 12
• Pages: 69-87
• Series Title: 3rd International Conference on Natural Language Processing & Computational Linguistics (NLPCL 2022)
• Series ISSN: 2231 - 5403
• Book Title: David C. Wyld et al. (Eds): SIPP, NLPCL, BIGML, SOEN, AISC, NCWMC, CCSIT - 2022 pp. 69-87, 2022. CS & IT - CSCP 2022
• ISBN: 978-1-925953-72-5
• DOI: https://doi.org/10.5121/csit.2022.121306
• Keywords: Dialogue Systems; Chatbot; Conversational Agents; AI; Natural Language Processing; Quality Attributes
• Public URL: https://uwe-repository.worktribe.com/output/8535323
• Publisher URL: https://airccse.org/csit/V12N13.html
• Related Public URLs: https://ccsit2022.org/nlpcl/index; ; https://aircconline.com/csit/papers/vol12/