Date: 27 February 2023
Time: 16:00 (CET)
Title: Chatbots for Second Language Learning
Abstract: It is estimated that over one billion people are currently learning English as a second language worldwide. Dialog systems could support second language conversational skill training via acting as engaging native conversational partners. This talk will cover three projects on this topic. We will first talk about how to obtain a coherent chatbot that can talk about a specific topic with users without massive conversational training data by leveraging large pre-trained language models. Then we will talk about how to distill different curriculums, such as vocabulary and grammar knowledge in chatbots through constrained neural decoding. Finally, we will talk about the design of a chatbot that can prompt users to perform self-corrections on grammar errors during conversations.
Speaker Biography: Zhou Yu is an Associate Professor at Columbia University Computer Science Department. Before that, she was an Assistant Professor at UC Davis. She obtained her Ph.D. from Carnegie Mellon University in 2017. Dr. Yu has built various dialog systems with major practical impacts, such as a job interview training system, a depression screening system, an Alexa social chatbot, and a second language learning system. Her research interest includes dialog systems, language understanding and generation, vision and language, human-computer interaction, and social robots. Dr. Yu's work earned a 2019 ACL best paper award nomination. She was recognized in the Forbes 2018 30 under 30 in Science and won the 2018 Amazon Alexa Prize. Zhou also is the CEO of Aritculate AI Inc which is a startup focusing on providing online second-language communication training using AI.