Conversational AI

Recent work has shown that self-supervised dialog-specific pretraining on large conversational datasets yields substantial gains over traditional language modeling (LM) pretraining in downstream task-oriented dialog (TOD). These approaches, however, …

The social impact of natural language processing and its applications has received increasing attention. In this position paper, we focus on the problem of safety for end-to-end conversational AI. We survey the problem landscape therein, introducing …