Interactively Teaching Machines with Natural Languages

Thursday, May 6, 2021, 11:00 am - 12:00 pm PDTiCal
VirtualThis event is open to the public.
NL Seminar
Zhou Yu (Columbia University)
Video Recording:

Reminder: ​Meeting hosts only admit guests that they know to the Zoom meeting. Hence, you're highly encouraged to use your USC account to sign into Zoom. If you're an outside visitor, please inform beforehand so we'll be aware of your attendance and let you in.

Humans routinely learn new concepts using natural language communications, even in scenarios with limited or no labeled examples. Interactions are another key aspect of human learning as well. Learning to ask good questions is a key step towards effective learning.  Can machines do the same?  In this talk, we will talk about how can a machine learn to ask good natural language questions and plan dynamically what questions to ask next to learn tasks effectively in low-resource settings.

Zhou Yu joined the CS department at Columbia University in Jan 2021 as an Assistant Professor. Before that, she was an Assistant Professor at UC Davis. She obtained her Ph.D. from Carnegie Mellon University in 2017.  Zhou has built various dialog systems that have a real impact, such as a job interview training system, a depression screening system, 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. Zhou received an ACL 2019 best paper nomination, featured in Forbes 2018 30 under 30 in Science, and won the 2018 Amazon Alexa Prize.

Recording approved by Speaker

The recording will be posted on USC/ISI's YouTube site within 1-2 business days from the date of the presentation.

« Return to Upcoming Events