Ran Zhao

TL;DR: This paper proposed a conditional variational autoencoder to learn a distribution over potential conversational intents and generate diverse responses using only greedy decoders, which can capture the discourse-level diversity in the encoder.

TL;DR: This paper uses existing literature and a corpus of peer tutoring data to develop a framework able to explain how humans in dyadic interactions build, maintain, and destroy rapport through the use of specific conversational strategies that function to fulfill specific social goals, and that are instantiated in particular verbal and nonverbal behaviors.

TL;DR: SARA (Socially-Aware Robot Assistant) is an embodied intelligent personal assistant that analyses the user’s visual, vocal, and verbal behaviours to estimate its rapport level with the user, and uses its own appropriateVisual, vocal and verbal behaviors to achieve task and social goals.

TL;DR: This work mined a reciprocal peer tutoring corpus reliably annotated for nonverbals like eye gaze and smiles, conversational strategies like self-disclosure and social norm violation, and for rapport, and performed a fine-grained investigation of how the temporal profiles of sequences of interlocutor behaviors predict increases and decreases of rapport.