Monica Lam: 2017 Plenary Session

 

Tuesday, April 11, 2017
Location: McCaw Hall, Arrillaga Alumni Center

"Almond: An Open Crowdsourced Programmable Virtual Assistant for the Internet of Things"

2:20PM

Abstract:

This talk presents the architecture of Almond, an open, crowdsourced, privacy-preserving and programmable virtual assistant for online services and the Internet of Things (IoT). Almond is the first assistant prototype that lets users specify trigger-action tasks in natural language.

Almond addresses four challenges in virtual assistant technology: generality, interoperability, privacy, and usability. For generality, we have created Thingpedia, a crowdsourced public knowledge base of open APIs and their natural language interfaces. Interoperability is provided by ThingTalk, a high-level domain-specific language that connects multiple devices or services via open APIs. For privacy, user credentials and user data are managed by our open-source ThingSystem, which can be run on personal phones or home servers. Finally, for usability, we use machine learning techniques to automatically translate natural language into trigger-action tasks.


Bio:

Monica Lam is a Professor of Computer Science and Director of the Mobile and Social Computer Laboratory. She received her BS in Computer Science from University of British Columbia and her PhD in Computer Science from Carnegie Mellon University. Her research interests spanned high-performance computing, computer architecture, compiler optimizations, security analysis, virtualization, mobile computing, and social networks. She is an author of the Dragon book, and an ACM Fellow.