Towards Evaluation of Multi-party Dialogue Systems

Abstract

Recent research in the field of conversational AI has emphasized the need for standardization of the metrics used in evaluation. In this work, we focus on evaluation methods used for multi-party dialogue systems. We present an expanded taxonomy focusing on multi-party dialogue based on the need for evaluation dimensions that address challenges associated with the presence of multiple participants. We also survey the evaluation metrics utilized in current multi-party dialogue research, and present our findings with regards to inconsistencies within existing work. Furthermore, we discuss the subsequent need to have more consistent evaluation methodologies and benchmarks. We motivate how consistency will contribute towards a better understanding of progress in the field of multi-party dialogue systems.