Identifying Spurious Correlations for Robust Text Classification

Zhao Wang, Aron Culotta


Abstract
The predictions of text classifiers are often driven by spurious correlations – e.g., the term “Spielberg” correlates with positively reviewed movies, even though the term itself does not semantically convey a positive sentiment. In this paper, we propose a method to distinguish spurious and genuine correlations in text classification. We treat this as a supervised classification problem, using features derived from treatment effect estimators to distinguish spurious correlations from “genuine” ones. Due to the generic nature of these features and their small dimensionality, we find that the approach works well even with limited training examples, and that it is possible to transport the word classifier to new domains. Experiments on four datasets (sentiment classification and toxicity detection) suggest that using this approach to inform feature selection also leads to more robust classification, as measured by improved worst-case accuracy on the samples affected by spurious correlations.
Anthology ID:
2020.findings-emnlp.308
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3431–3440
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.308
DOI:
10.18653/v1/2020.findings-emnlp.308
Bibkey:
Cite (ACL):
Zhao Wang and Aron Culotta. 2020. Identifying Spurious Correlations for Robust Text Classification. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3431–3440, Online. Association for Computational Linguistics.
Cite (Informal):
Identifying Spurious Correlations for Robust Text Classification (Wang & Culotta, Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.308.pdf
Video:
 https://slideslive.com/38940117
Code
 tapilab/emnlp-2020-spurious