Existing studies in dialogue system research mostly treat task-oriented
...
As task-oriented dialog systems are becoming increasingly popular in our...
Zero-shot transfer learning for dialogue state tracking (DST) enables us...
Zero-shot cross-domain dialogue state tracking (DST) enables us to handl...
Continual learning in task-oriented dialogue systems can allow us to add...
Motivated by the needs of resource constrained dialog policy learning, w...
The existing dialogue corpora and models are typically designed under tw...
Open-ended human learning and information-seeking are increasingly media...
Traditional recommendation systems produce static rather than interactiv...
Natural language understanding and dialogue policy learning are both
ess...