Percy Liang

Research Area

Computer Science, Language Processing

Institution

Stanford University

My research is to develop trustworthy agents that can communicate effectively with people and improve over time through interaction. I broadly identify with the machine learning (ICML, NIPS) and natural language processing (ACL, NAACL, EMNLP) communities.

Agents need to be able to “understand natural language.” Much of my work has centered around the task of converting a user’s request to simple computer programs that specify the sequence of actions to be taken in response. Check out this friendly introduction to natural language interfaces (XRDS magazine 2014) or this survey article on executable semantic parsing (CACM 2016). We’ve also created the SQuAD dataset to advance research on reading comprehension. Recently, we’ve been exploring agents that learn language interactively (ACL 2017), or can engage in a collaborative dialogue with humans (ACL 2017).

Despite the successes of machine learning, notably deep learning, otherwise high-performing models are still difficult to debug and fail catastrophically in the presence of changing data distributions and adversaries. Given our increasingly reliance on machine learning, it is critical to build tools to help us make machine learning more reliable “in the wild.” Recently, we’ve worked on estimating the accuracy of a predictor on an unknown distribution (NIPS 2016), using influence functions to understand black-box models (ICML 2017), and trying to provide formal guarantees that a learning algorithm is safe from adversaries.

Finally, I am a strong proponent of efficient and reproducible research. We have been developing CodaLab Worksheets in collaboration with Microsoft Research, a new platform that allows researchers to maintain the full provenance of an experiment from raw data to final results. Most of our recent papers have been published on CodaLab as executable papers. We are actively looking for contributors, so please contact me if you’re interested!