Stanford Open Virtual Assistant Lab

Open Virtual Assistant Manifesto

• Democratize AI for linguistic user interfaces. We should have open, collaborative research to put open-source linguistic technology in the hands of all businesses. (The LUInet project)
• An open non-proprietary linguistic web. All skills, or linguistic user interfaces, should be made available to any virtual assistant. (The Thingpedia project)
• Sharing with individual data ownership. Consumers should have a choice in virtual assistant services and the ability to control how we share our data. (The Almond project)

We are starting a world-wide open-source initiative, Open Virtual Assistant Lab (OVAL), to create an ecosystem founded on open virtual assistant technology. OVAL is supported by the National Science Foundation under Grant No. 1900638. This project gathers together experts in distributed systems, programming languages, natural language processing, machine learning, knowledge engineering, security, human-computer interaction, and crowdsourcing to create the world’s best virtual assistant.

Presentations & Interviews

• "Stanford Team Aims at Alexa and Siri With a Privacy-Minded Alternative", John Markoff for the New York Times, 6/14/2019
• "Privacy in the age of virtual assistants", Russ Altman for the Future of Everything (podcast), 6/4/2019
• "Giving Control Back to Consumers with Open Federated Virtual Assistants", Monica Lam, Keynote at HiPEAC 2019, 1/21/2019
• "Keeping the Internet Open with an Open-Source Virtual Assistant", Monica Lam, Keynote at Mobicom 2018, 11/1/2018

Current Projects

Almond

Almond is a general-purpose, federated virtual assistant that respects the user's privacy by running on-device and offering flexible access control.

Thingpedia

An open, crowdsourced repository of Web and Internet of Things APIs, their metadata and all the ways to express them in natural language.

LUInet

An open-source dataset and model for natural language understanding in virtual assistants, as well as tools to acquire data and extend it to new domains.

Brassau

Brassau combines voice with automatically generated graphical user interfaces to take advantage of the best of each modality.

Publications

2019

• Genie: A Generator of Natural Language Semantic Parsers for Virtual Assistant Commands
  Giovanni Campagna, Silei Xu, Mehrad Moradshahi, Richard Socher, and Monica S. Lam
  In Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation (to appear), Phoenix, AZ, June 2019.
  Artifact — Dataset

2018

• Controlling Fine-Grain Sharing in Natural Language with a Virtual Assistant
  Giovanni Campagna, Silei Xu, Rakesh Ramesh, Michael Fischer, and Monica S. Lam
  In Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT), 2018.
• Brassau: Automatically Generating Graphical User Interfaces for Virtual Assistants
  Michael Fischer, Giovanni Campagna, Silei Xu, and Monica S. Lam
  In 20th International Conference on Human-Computer Interaction with Mobile Devices and Services. (MobileHCI), 2018.

2017

• Almond: The Architecture of an Open, Crowdsourced, Privacy-Preserving, Programmable Virtual Assistant
  Giovanni Campagna, Rakesh Ramesh, Silei Xu, Michael Fischer, and Monica S. Lam
  In Proceedings of the 26th International World Wide Web Conference (WWW), Perth, Australia, April 2017.

Team

Senior Members

• Prof. Monica Lam (PI, CS)
• Prof. Michael Bernstein (CS)
• Prof. Dan Boneh (CS)
• Dr. Edward Y. Chang
  President of Research and Healthcare, HTC
• Dr. Jen King (Law)
• Prof. James Landay (CS)
• Prof. Fei-Fei Li (CS)
• Prof. Chris Manning (CS)
• Prof. David Mazieres (CS)
• Prof. Chris Re (CS)
• Dr. Richard Socher
  Chief Scientist, Salesforce

Students

• Giovanni Campagna
• Michael Fischer
• Jian Li
• Mehrad Moradshahi
• Silei Xu
• Jackie Yang
• Richard Yang

Previous members of our team include Albert Chen, Zhiyang He, Jiaqi Xue, Aashna Garg, Jiwon Seo, Sadjad Fouladi, Reynis Vazquez, Rakesh Ramesh. We thank them for their valuable contribution.