Scholar
Giovanni Campagna
Google Scholar ID: fOioY3wAAAAJ
Researcher, Bardeen Inc.
Citations & Impact
Citations
593
H-index
12
i10-index
16
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- - Selected publications include:
- - A Few-Shot Semantic Parser for Wizard-of-Oz Dialogues with the Precise ThingTalk Representation
- - DIY Assistant: A Multi-Modal End-User Programmable Virtual Assistant
- - Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking
- - Genie: A Generator of Natural Language Semantic Parsers for Virtual Assistant Commands
- - Controlling Fine-Grain Sharing in Natural Language with a Virtual Assistant
- - Almond: The Architecture of an Open, Crowdsourced, Privacy-Preserving, Programmable Virtual Assistant
Research Experience
- - Currently working at Bardeen, researching ways to make automations easier to specify by end-users.
- - Previously, a member of the Stanford Open Virtual Assistant Lab (OVAL), working with Prof. Monica Lam on the Genie project, an open source privacy-preserving virtual assistant platform.
Education
- Graduated with a PhD in Computer Science from Stanford University in January 2022, under the supervision of Prof. Monica Lam.
Background
- A software engineer and ML/NLP researcher living in California.
Miscellany
- Was a developer and a member of the GNOME community from 2011 to about 2015, developing GNOME Shell and Mutter, as well as maintaining libgweather and GNOME Weather. Nowadays, mostly writes Node.js and maintains several modules.
Co-authors