Perspectives for Evaluating Conversational AI
This work addresses the challenge of defining and measuring success in conversational AI for developers and researchers, though it is incremental as it builds on existing evaluation frameworks.
The paper tackles the problem of evaluating the success of search-oriented conversational AI systems by proposing four evaluation perspectives: user experience, information retrieval, linguistic, and artificial intelligence, while also discussing background details, personalization, and current challenges.
Conversational AI systems are becoming famous in day to day lives. In this paper, we are trying to address the following key question: To identify whether design, as well as development efforts for search oriented conversational AI are successful or not.It is tricky to define 'success' in the case of conversational AI and equally tricky part is to use appropriate metrics for the evaluation of conversational AI. We propose four different perspectives namely user experience, information retrieval, linguistic and artificial intelligence for the evaluation of conversational AI systems. Additionally, background details of conversational AI systems are provided including desirable characteristics of personal assistants, differences between chatbot and an AI based personal assistant. An importance of personalization and how it can be achieved is explained in detail. Current challenges in the development of an ideal conversational AI (personal assistant) are also highlighted along with guidelines for achieving personalized experience for users.