# Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detection

arXiv: https://arxiv.org/abs/2203.12536 · HTML: https://mlsanity.com/paper/2203.12536/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 44 references that are in the map.
- First posted on arXiv 23 Mar 2022.

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Is Attention Interpretable?](https://mlsanity.com/paper/1906.03731/) (2019)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection](https://mlsanity.com/paper/2012.15761/) (2020)
- [Deep Learning for Hate Speech Detection in Tweets](https://mlsanity.com/paper/1706.00188/) (2017)
- [Debugging Tests for Model Explanations](https://mlsanity.com/paper/2011.05429/) (2020)
- [Interpretations are useful: penalizing explanations to align neural networks with prior knowledge](https://mlsanity.com/paper/1909.13584/) (2019)
- [A BERT-Based Transfer Learning Approach for Hate Speech Detection in Online Social Media](https://mlsanity.com/paper/1910.12574/) (2019)
- [Contextualizing Hate Speech Classifiers with Post-hoc Explanation](https://mlsanity.com/paper/2005.02439/) (2020)
- [Incorporating Priors with Feature Attribution on Text Classification](https://mlsanity.com/paper/1906.08286/) (2019)
- [Towards generalisable hate speech detection: a review on obstacles and solutions](https://mlsanity.com/paper/2102.08886/) (2021)
- [Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classification](https://mlsanity.com/paper/1908.11860/) (2019)
- [PERL: Pivot-based Domain Adaptation for Pre-trained Deep Contextualized Embedding Models](https://mlsanity.com/paper/2006.09075/) (2020)
- [Refining Language Models with Compositional Explanations](https://mlsanity.com/paper/2103.10415/) (2021)
- [Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models](https://mlsanity.com/paper/1911.06194/) (2019)
- [An Empirical Study on Explanations in Out-of-Domain Settings](https://mlsanity.com/paper/2203.00056/) (2022)
- [Knowledge Distillation for BERT Unsupervised Domain Adaptation](https://mlsanity.com/paper/2010.11478/) (2020)
- [Towards non-toxic landscapes: Automatic toxic comment detection using DNN](https://mlsanity.com/paper/1911.08395/) (2019)
- [Adversarial Augmentation Policy Search for Domain and Cross-Lingual Generalization in Reading Comprehension](https://mlsanity.com/paper/2004.06076/) (2020)
- [Unsupervised Domain Adaptation for Hate Speech Detection Using a Data Augmentation Approach](https://mlsanity.com/paper/2107.12866/) (2021)

## Built on by (most cited first, 3 of 3)

- [Robust Hate Speech Detection in Social Media: A Cross-Dataset Empirical Evaluation](https://mlsanity.com/paper/2307.01680/) (2023)
- [Calibration Meets Explanation: A Simple and Effective Approach for Model Confidence Estimates](https://mlsanity.com/paper/2211.03041/) (2022)
- [Domain Classification-based Source-specific Term Penalization for Domain Adaptation in Hate-speech Detection](https://mlsanity.com/paper/2209.08681/) (2022)

## Abstract (arXiv)

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.