קולקוויום מחלקתי 27.12.23

Usual Time
יום חמישי 27.12.23 בשעה 16:00
Place
VIA ZOOM : https://us02web.zoom.us/j/83383478356
More Details

DR. AMIR FEDER

Columbia University

Causally-driven ML for Text

 

Understanding causal relationships is a key objective in scientific research, yet its role in machine learning (ML) remains underemphasized. Recent progress in ML, particularly with the advent of large language models (LLMs), has been fueled by extracting correlations from large datasets using neural architectures. However, despite their success, correlational predictive models can be untrustworthy: they rely on shortcuts in the data, leading to errors when applied to out-of-distribution settings; and their representation of text lacks interpretability, rendering them unsuitable for scientific inquiry. 

 

In this talk, I will show how a causal perspective can mitigate these shortcomings. I will present novel causally-driven methods that remove predictor reliance on shortcuts and thus lead to improved out-of-distribution performance. Then, I will briefly describe how to build probabilistic models of text tailored for estimating causal effects. Finally, I will conclude by laying out my vision for the future of causally-driven ML for text.

 

Short Bio

Amir Feder is a postdoctoral fellow at the Columbia University Data Science Institute, working with David Blei. He is currently also a visiting faculty researcher at Google Research. He works in the field of machine learning and causal inference, with a focus on text data. His research develops methods that integrate causality into natural language processing (NLP) to improve the reliability of NLP systems, and to facilitate scientific inquiry with text data. He was a co-organizer of the First Workshop on NLP and Causal Inference (CI+NLP) at EMNLP 2021, the Tutorial on Causality for NLP at EMNLP 2022, and the Workshop on Spurious Correlations, Invariance and Stability at ICML 2023.

 

Before joining Columbia, Amir received his PhD from the Technion, where he was advised by Roi Reichart and worked closely with Uri Shalit. In a previous (academic) life, he was an economics, statistics and history student at Tel Aviv University, the Hebrew University of Jerusalem and Northwestern University.

ONLY VIA ZOOM

https://us02web.zoom.us/j/83383478356