David Gaddy

I am a Ph.D. student in the Natural Language Processing Group at UC Berkeley, advised by Dan Klein. My current research is on decoding silent speech with electromyography. This work aims to recognize silently mouthed words and turn them into audible speech or text, using electrical signals from muscles of the face. I have also worked on a range of other topics, including language grounding, semantic parsing, and syntactic parsing. I did my undergraduate studies at MIT and have interned at FAIR and Google.

Email: dgaddy@berkeley.edu

Silent Speech Publications

Digital Voicing of Silent Speech
David Gaddy and Dan Klein
Best Paper Award EMNLP 2020. [code] [data] [video]

An Improved Model for Voicing Silent Speech
David Gaddy and Dan Klein
ACL 2021. [code]

Other Publications

Interactive Assignments for Teaching Structured Neural NLP
David Gaddy, Daniel Fried, Nikita Kitaev, Mitchell Stern, Rodolfo Corona, John DeNero, and Dan Klein
Teaching NLP Workshop, NAACL 2021. [materials]

Overcoming Conflicting Data for Model Updates
David Gaddy, Alex Kouzemtchenko, Pavan Kumar Reddy, Prateek Kolhar, and Rushin Shah
arXiv preprint. [data]

Pre-Learning Environment Representations for Data-Efficient Neural Instruction Following
David Gaddy and Dan Klein
ACL 2019. [code] [slides] [blog]

What’s Going On in Neural Constituency Parsers? An Analysis
David Gaddy, Mitchell Stern, and Dan Klein
NAACL 2018. [code] [poster]

Ten Pairs to Tag - Multilingual POS Tagging via Coarse Mapping between Embeddings
Yuan Zhang, David Gaddy, Regina Barzilay, and Tommi Jaakkola
NAACL 2016. [code]