P
Percy Liang
Researcher at Stanford University
Publications - 369
Citations - 42254
Percy Liang is an academic researcher from Stanford University. The author has contributed to research in topics: Computer science & Parsing. The author has an hindex of 75, co-authored 306 publications receiving 29242 citations. Previous affiliations of Percy Liang include University of California, Berkeley & Google.
Papers
More filters
Posted Content
Can Small and Synthetic Benchmarks Drive Modeling Innovation? A Retrospective Study of Question Answering Modeling Approaches.
TL;DR: In this paper, the authors conduct a retrospective study of 20 SQuAD modeling approaches, investigating how well 32 existing and synthesized benchmarks concur with the SQUAD question answering benchmark.
Posted Content
Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
Sumanth Dathathri,Krishnamurthy Dvijotham,Alexey Kurakin,Aditi Raghunathan,Jonathan Uesato,Rudy Bunel,Shreya Shankar,Jacob Steinhardt,Ian Goodfellow,Percy Liang,Pushmeet Kohli +10 more
TL;DR: In this article, a first-order dual semidefinite programming (SDP) algorithm was proposed to verify robustness to adversarial perturbations in verification-agnostic networks.
Posted Content
Inferring Multidimensional Rates of Aging from Cross-Sectional Data
Emma Pierson,Pang Wei Koh,Tatsunori Hashimoto,Daphne Koller,Jure Leskovec,Nicholas Eriksson,Percy Liang +6 more
TL;DR: In this article, an interpretable latent-variable model that learns temporal dynamics from cross-sectional data was proposed to represent each individual's features over time as a nonlinear function of a low-dimensional, linearly evolving latent state.
Proceedings ArticleDOI
No, to the Right: Online Language Corrections for Robotic Manipulation via Shared Autonomy
TL;DR: This article proposed Language-Informed Latent Actions with Corrections (LILAC), a framework for incorporating and adapting to natural language corrections "to the right", or "no, towards the book" during execution.
Patent
Data collection for a new conversational dialogue system
Percy Liang,Daniel Klein,Laurence S. Gillick,Jordan Cohen,Linda Kathleen Arsenault,Joshua James Clausman,Adam Pauls,David Hall +7 more
TL;DR: In this paper, a data collection system is based on a general set of dialogue acts which are derived from a database schema, and crowds workers perform two types of tasks: (i) identification of sensical dialogue paths and (ii) performing context-dependent paraphrasing of these dialogue paths into real dialogues.