Abstract

In the past decade, task-oriented dialogue systems have been the most prominent component in today's virtual personal assistants (VPAs). Among these VPAs, Microsoft's Cortana, Apple's Siri, Amazon Alexa, Google Assistant, and Facebook's Bot, have incorporated dialogue modules in various devices, which allow users to speak naturally in order to finish tasks more efficiently. The traditional conversational systems have rather complex and/or modular pipelines. The advance of deep learning has recently risen the applications of neural models to dialogue modeling. However, applying deep learning for building robust and scalable dialogue systems is still challenging as it requires deeper understanding and detailed knowledge for dialogue research work. Thus, this talk focuses on an overview of the dialogue system development while describing most recent research for dialogue systems, and summarizing the challenges.

Bio

Yun-Nung (Vivian) Chen is an assistant professor in the Department of Computer Science and Information Engineering at National Taiwan University. Her research interests include language understanding, dialogue systems, natural language processing, deep learning, and multimodality. She received the Google Faculty Research Awards, Best Student Paper Awards from IEEE ASRU 2013 and IEEE SLT 2010 and a Student Best Paper Nominee from INTERSPEECH 2012. Chen earned the Ph.D. degree from School of Computer Science at Carnegie Mellon University, Pittsburgh in 2015, and then worked for Microsoft Research in the Deep Learning Technology Center in 2016 prior to joining NTU. (http://vivianchen.idv.tw)

All faculties and students are welcome to join.