This National Science Foundation (NSF) Project Grant under the Computer and Information Science and Engineering (CFDA 47.070) program provides $260,047 to the University of Washington to develop an intelligent conversational agent that can conduct two-way, proactive conversations, generate new insights, and make novel contributions.
The project will build the conversational agent using a hierarchical model-based deep reinforcement learning framework. The framework will enable the agent to dynamically detect opportunities to expand the conversation, manage multi-tiered task objectives, and propose proactive responses. The system will be evaluated through offline experiments, crowdsourcing, and user studies to assess its effectiveness, novelty, and user experience. No sub-awards are planned for this 3-year award, which runs from June 2024 to May 2027.
Generated 1/28/25, 10:39 AM