Aron Culotta


pdf bib
Enhancing Model Robustness and Fairness with Causality: A Regularization Approach
Zhao Wang | Kai Shu | Aron Culotta
Proceedings of the First Workshop on Causal Inference and NLP

Recent work has raised concerns on the risk of spurious correlations and unintended biases in statistical machine learning models that threaten model robustness and fairness. In this paper, we propose a simple and intuitive regularization approach to integrate causal knowledge during model training and build a robust and fair model by emphasizing causal features and de-emphasizing spurious features. Specifically, we first manually identify causal and spurious features with principles inspired from the counterfactual framework of causal inference. Then, we propose a regularization approach to penalize causal and spurious features separately. By adjusting the strength of the penalty for each type of feature, we build a predictive model that relies more on causal features and less on non-causal features. We conduct experiments to evaluate model robustness and fairness on three datasets with multiple metrics. Empirical results show that the new models built with causal awareness significantly improve model robustness with respect to counterfactual texts and model fairness with respect to sensitive attributes.


pdf bib
Identifying Spurious Correlations for Robust Text Classification
Zhao Wang | Aron Culotta
Findings of the Association for Computational Linguistics: EMNLP 2020

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.


pdf bib
Inferring latent attributes of Twitter users with label regularization
Ehsan Mohammady Ardehaly | Aron Culotta
Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies


pdf bib
Using County Demographics to Infer Attributes of Twitter Users
Ehsan Mohammady | Aron Culotta
Proceedings of the Joint Workshop on Social Dynamics and Personal Attributes in Social Media


pdf bib
A Demographic Analysis of Online Sentiment during Hurricane Irene
Benjamin Mandel | Aron Culotta | John Boulahanis | Danielle Stark | Bonnie Lewis | Jeremy Rodrigue
Proceedings of the Second Workshop on Language in Social Media


pdf bib
First-Order Probabilistic Models for Coreference Resolution
Aron Culotta | Michael Wick | Andrew McCallum
Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference


pdf bib
Learning Field Compatibilities to Extract Database Records from Unstructured Text
Michael Wick | Aron Culotta | Andrew McCallum
Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing

pdf bib
Practical Markov Logic Containing First-Order Quantifiers with Application to Identity Uncertainty
Aron Culotta | Andrew McCallum
Proceedings of the Workshop on Computationally Hard Problems and Joint Inference in Speech and Language Processing

pdf bib
Integrating Probabilistic Extraction Models and Data Mining to Discover Relations and Patterns in Text
Aron Culotta | Andrew McCallum | Jonathan Betz
Proceedings of the Human Language Technology Conference of the NAACL, Main Conference


pdf bib
Dependency Tree Kernels for Relation Extraction
Aron Culotta | Jeffrey Sorensen
Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04)

pdf bib
Confidence Estimation for Information Extraction
Aron Culotta | Andrew McCallum
Proceedings of HLT-NAACL 2004: Short Papers