Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detection

TL;DR

This paper introduces a dynamic regularization method using attribution techniques to automatically identify and mitigate spurious correlations in hate speech classifiers, enhancing their cross-corpora generalization.

Contribution

It proposes a novel, flexible approach that dynamically refines regularization terms during training, outperforming static dictionary-based methods for hate speech detection.

Findings

Improved cross-corpora performance over previous methods

Automatic identification of spurious correlations

Effective combination with existing dictionary-based approaches

Abstract

Hate speech classifiers exhibit substantial performance degradation when evaluated on datasets different from the source. This is due to learning spurious correlations between words that are not necessarily relevant to hateful language, and hate speech labels from the training corpus. Previous work has attempted to mitigate this problem by regularizing specific terms from pre-defined static dictionaries. While this has been demonstrated to improve the generalizability of classifiers, the coverage of such methods is limited and the dictionaries require regular manual updates from human experts. In this paper, we propose to automatically identify and reduce spurious correlations using attribution methods with dynamic refinement of the list of terms that need to be regularized during training. Our approach is flexible and improves the cross-corpora performance over previous work independently and in combination with pre-defined dictionaries.