University of Cambridge > > Language Technology Lab Seminars > Learning the Difference that Makes a Difference with Counterfactually Augmented Data

Learning the Difference that Makes a Difference with Counterfactually Augmented Data

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Marinela Parovic.

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 some recent follow-up work.

This talk is part of the Language Technology Lab Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2023, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity