In this talk, Dr. Choi will first explain key lessons from the Alexa Prize Socialbot Grand Challenge 3 and suggest a hybrid of three approaches, state machines, probabilistic reasoning, and deep learning, to build Conversational AI for practical applications. Dr. Choi will then provide a comprehensive analysis of chatbot evaluation that compares four state-of-the-art dialogue models, revealing their strengths and weaknesses to simulate the current state of human-computer interaction. Finally, Dr. Choi will present his recent effort to integrate Conversational AI into higher education, which can vastly enhance the college experience, facilitate interactions between students and professors, as well as guide students for better academic and career development.
Dr. Jinho Choi is an associate professor of Computer Science, Quantitative Theory and Methods, and Linguistics at Emory University. Dr. Choi has been active in the field of Natural Language Processing (NLP). He has presented many state-of-the-art NLP models that automatically derive various linguistic structures from plain text, which are publicly available in the NLP Toolkit called ELIT. He has also led the Character Mining project and introduced novel machine comprehension tasks for explicit and implicit understanding in multiparty dialogue. For the application side, Dr. Choi has developed innovative Biomedical NLP models by collaborating with several medical fields such as radiology, neurology, transplant, and nursing. His latest research focuses on building the conversational AI-based chatbot called Emora that aims to be a daily companion in everyone’s life. With Emora, Dr. Choi’s team won 1st-place at the Alexa Prize Socialbot Grand Challenge 3, which came with a $500,000 cash award.