Day 1

Large-Scale Deep Learning with Structure
Sujith Ravi / SliceX AI
Homepage
Unlikelihood-training and back-training for robust natural language understanding
Siva Reddy / McGill
Homepage
Scaling the world wide voice web with open standards and pretrained semantic parsers
Monica Lam / Stanford
Homepage
Knowledge, Language Models, and Adaptation
Percy Liang / Stanford
Homepage
Systematic reasoning with language models
Peter Clark / Allen Institute for AI
Homepage

Day 2

Learning health knowledge bases
David Sontag / MIT
Homepage
Learning symbolic rules for reasoning
Jia Deng / Princeton
Homepage
Vision & language
Devi Parikh / Georgia Tech and Facebook AI Research
Homepage
Extracting knowledge from text about models and workflows: transparency, reproducibility, and automation in science
Yolanda Gil / USC
Homepage

Day 3

Citizen data scientists: how to empower your workforce to make data driven decisions
Tim Kraska / MIT
Homepage
Why natural language is the right vehicle for complex reasoning
Greg Durrett / University of Texas Austin
Homepage
Accelerating innovation through analogy mining
Dafna Shahaf / Hebrew University
Homepage
Knowledge-rich, robust neural text comprehension and reasoning
Hanna Hajishirzi / University of Washington
Homepage