Yong-Seok Choi

Dialogue Act-Aided Backchannel Prediction Using Multi-Task Learning

Produced in the form of small injections such as "Yeah!" or "Uh-Huh" by listeners in a conversation, supportive verbal feedback (i.e., backchanneling) is essential for natural dialogue. Highlighting its tight relation to speaker intent and utterance type, we propose a multi-task learning approach th…