|Title:||The Architecture of an Open, Crowdsourced, Privacy-Preserving, Programmable Virtual Assistant|
|Date:||March 22, 2017 (Wednesday)|
|Time:||11:00 a.m. - 12:00 n.n.|
|Venue:||Room 121, 1/F, Ho Sin-hang Engineering Building,
The Chinese University of Hong Kong,
|Speaker:||Prof. Monica Lam
Department of Computer Science
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). Our proposal addresses four challenges in virtual assistant technology: generality, interoperability, privacy, and usability. Generality is addressed by crowdsourcing Thingpedia, an open 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, the virtual assistant has a natural language interface that can be trained with the help of a menu-driven interface.
We have created a fully working prototype, and crowdsourced a set of 187 functions across 45 different kinds of devices. Almond is the first virtual assistant that lets users specify trigger-action tasks in natural language. Despite the lack of real usage data, our experiment suggests that Almond can understand about 40% of the complex tasks when uttered by a user familiar with its capability.
Dr. Monica Lam has been a Professor of Computer Science at Stanford University since 1988 and is the Faculty Director of the Stanford MobiSocial Computing Laboratory. She received a B. Sc. with honors from University of British Columbia and a PhD in computer science from Carnegie Mellon University in 1987.
She has published widely on a large range of topics in computer science. Her current research focus is to develop open virtual assistant technology that protects user privacy and fosters an open ecosystem. Her past research contributions include the architecture and compiler technology for the first high-performance systolic machine and large-scale coherent shared memory machines, deep program analysis to find security vulnerabilities in programs, and open mobile infrastructure that enables easy data sharing without loss of privacy.
Lam is a Fellow of the Association of Computing Machinery (ACM). She received an NSF Young Investigator award in 1992, and has won many best paper awards from the ACM. She is a co-author of the "classic definitive compiler technology text", according to Wikipedia, which is popularly known as the "dragon book". The textbook has been translated into Chinese, French, German, Italian, Japanese, Korean, Portuguese, Russian and Spanish. Many of her research results have been adopted in the industry by large companies as well as startups.
Enquiries: Miss Ricola Lo at tel 3943 8439
For more information, please refer to http://www.cse.cuhk.edu.hk/seminar.