Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions
Computation and Language
2020-07-14 v2 Artificial Intelligence
Abstract
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.
Cite
@article{arxiv.2006.12442,
title = {Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions},
author = {Stephen Roller and Y-Lan Boureau and Jason Weston and Antoine Bordes and Emily Dinan and Angela Fan and David Gunning and Da Ju and Margaret Li and Spencer Poff and Pratik Ringshia and Kurt Shuster and Eric Michael Smith and Arthur Szlam and Jack Urbanek and Mary Williamson},
journal= {arXiv preprint arXiv:2006.12442},
year = {2020}
}