Institute of Information Science, Academia Sinica

We have envisioned that one day computers will understand natural language and actively predict what and when we need help in order to proactively complete tasks on our behalf. When computers become more ubiquitous (e.g. wearable devices) and number of applications increases, there has been a tremendous investment of virtual personal assistants from the industry (Microsoft's Cortana, Google Home, Apple's Siri, Amazon's Echo, and Facebook's Bot). In this talk, we will give an overview of personal assistants, describe the system architecture and the key components. Then we will highlight challenges and recent trends driven by deep learning and big data, and discuss the systems' potential to fully redefine the human-computer interaction moving forward.

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 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 joined Microsoft Research for a research position in the Deep Learning Technology Center in 2016. (http://vivianchen.idv.tw)