The Open Virtual Assistant Lab (OVAL) is organizing the First Open Virtual Assistant Workshop to be held on , at Stanford University, as part of the Stanford HAI Fall Conference.

The purpose of the OVAL lab is to create an ecosystem with open, federated, state-of-the-art virtual assistants to accelerate linguistic technology, make technology openly available, accelerate adoption, and enable sharing with privacy.

The OVAL lab has created a first open-source, virtual assistant that supports sharing with privacy (Almond), an open skill platform (Thingpedia), and an open-source neural model (LUInet). We are creating an industrial affiliates program to accelerate our collaboration with industry partners.

We invite interested stakeholders, open-source community members, and researchers to participate in this working meeting. Our goals are:

  1. To publicise the project's efforts to-date, which includes open standard proposals, our community-building, collaborations with industry, and our research agenda.
  2. To broaden participation in the effort, solicit new contributions, and collect feedback.
  3. To create a plan of action for the next two years.

We are actively putting together the agenda; we welcome suggestions of topics and speakers.

This is an invitation-only workshop: we must limit attendance as it is a working meeting. If you are interested in an invitation, please contact describing your interest in participation.

A Tentative Agenda

Need Finding

A panel on the need for an open virtual assistant.

Bootstrapping the Ecosystem

Proposal for a Write-Once-Run-Anywhere (WORA) skill platform: Thingpedia (1.0).

Voice-to-text technology.

An open-source neural network for virtual assistants.

Training NL neural models without real user data.

Growing the skill platform.

Inter-operable, privacy-preserving virtual assistants.

Research agenda

Thingpedia 2.0. Multi-modal assistants with dialogs.

Answering questions about existing websites without manual skill creation.

Conversational agents: Engaging dialogs and neural models for dialogs.

Auditable, revocable 3rd-party sharing contracts with scalable blockchain technology.

Open Discussion

Workshop Co-Chairs

Prof. Monica Lam
Prof. James Landay