What we're about
Upcoming events (1)
Our June 2, 2021 program features Zack Lipton from Carnegie Mellon University, speaking on "Learning the Difference that Makes a Difference with Counterfactually Augmented Data." The program starts at 1 pm US-Eastern / 10 am US-Pacific / 6 pm UK / 7 pm CEST.
Abstract: Despite alarm over the reliance of machine learning systems on so-called spurious patterns, the term lacks coherent meaning in standard statistical frameworks. However, the language of causality offers clarity: spurious associations are due to confounding (e.g., a common cause), but not direct or indirect causal effects. Inspired by this literature (and borrowing from it gesturally), we address natural language processing, introducing methods and resources for training models less sensitive to spurious patterns. Given documents and their initial labels, we task humans with revising each document so that it (i) accords with a counterfactual target label; (ii) retains internal coherence; and (iii) avoids unnecessary changes. Interestingly, on sentiment analysis and natural language inference tasks, classifiers trained on original data fail on their counterfactually-revised counterparts and vice versa. Classifiers trained on combined datasets perform remarkably well, just shy of those specialized to either domain. I will discuss this method, the early results, some conceptual underpinnings of the approach, and recent follow-up work.
Speaker bio: Zachary Chase Lipton is the BP Junior Chair Assistant Professor of Operations Research and Machine Learning at Carnegie Mellon University and a Visiting Scientist at Amazon AI. He directs the Approximately Correct Machine Intelligence (ACMI) lab, whose research spans core machine learning methods, applications to clinical medicine and natural language processing, and the impact of automation on social systems. Current research focuses include robustness under distribution shift, decision-making, breast cancer screening, the effective and equitable allocation of organs, and the applications of causal thinking in practical high-dimensional settings that resist stylized causal models. He is the founder of the Approximately Correct blog (approximatelycorrect.com) and a co-author of Dive Into Deep Learning, an interactive open-source book drafted entirely through Jupyter notebooks. Find on Twitter (@zacharylipton) or GitHub (@zackchase), or the internet (acmilab.org).
By responding here, you acknowledge and consent to our Code of Conduct: We seek to provide a respectful, friendly, professional experience for everyone regardless of gender, sexual orientation, physical appearance, disability, age, race, and religion. We do not tolerate behavior that is harassing or degrading to any individual, in any form. Participants are responsible for knowing and abiding by these standards. We encourage all attendees to assist in creating a welcoming, safe, and respectful experience.