Break, Repair, Learn, Break Less: Investigating User Preferences for Assignment of Divergent Phrasing Learning Burden in Human-Agent Interaction to Minimize Conversational Breakdowns

Conversational agents (CA) occasionally fail to understand the user's intention or respond inappropriately due to natural language complexity. These conversational breakdowns can happen because of low intent and entity prediction confidence scores. A promising repair strategy in such cases is that the CA proposes to users likely alternatives...