Don't Forget Your ABC's: Evaluating the State-of-the-Art in Chat-Oriented Dialogue Systems

Sarah E. Finch, James D. Finch, Jinho D. Choi


Abstract

Despite tremendous advancements in dialogue systems, stable evaluation still requires human judgments producing notoriously high-variance metrics due to their inherent subjectivity.Moreover, methods and labels in dialogue evaluation are not fully standardized, especially for open-domain chats, with a lack of work to compare and assess the validity of those approaches.The use of inconsistent evaluation can misinform the performance of a dialogue system, which becomes a major hurdle to enhance it.Thus, a dimensional evaluation of chat-oriented open-domain dialogue systems that reliably measures several aspects of dialogue quality is desired.This paper presents a novel human evaluation method to estimate the rates of many dialogue system behaviors.Our method is used to evaluate four state-of-the-art open-domain dialogue systems and compared with existing approaches.The analysis demonstrates that our behavior method is more suitable than alternative Likert-style or comparative approaches for dimensional evaluation of these systems.

Venue / Year

Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL) / 2023

Links

Anthology | Paper | Presentation | BibTeX | GitHub