Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions
It addresses the challenge of building engaging and effective conversational AI for general users, but is incremental as it synthesizes existing research without presenting new results.
The paper reviews the current state of open-domain conversational agents, focusing on qualities like continual learning, engaging content, and well-behaved interactions, and discusses gaps and future directions based on the authors' group work.
We present our view of what is necessary to build an engaging open-domain conversational agent: covering the qualities of such an agent, the pieces of the puzzle that have been built so far, and the gaping holes we have not filled yet. We present a biased view, focusing on work done by our own group, while citing related work in each area. In particular, we discuss in detail the properties of continual learning, providing engaging content, and being well-behaved -- and how to measure success in providing them. We end with a discussion of our experience and learnings, and our recommendations to the community.