Related papers: Noisy Self-Training with Data Augmentations for Offensive and Hate Speech Detection Tasks

Noisy Self-Training with Data Augmentations for Offensive and Hate Speech Detection Tasks

URL: http://arxiv.org/abs/2307.16609v1
Date: Mon, 31 Jul 2023 12:35:54 GMT
Title: Noisy Self-Training with Data Augmentations for Offensive and Hate Speech Detection Tasks
Authors: Jo\~ao A. Leite, Carolina Scarton, Diego F. Silva
Abstract summary: "Noisy" self-training approaches incorporate data augmentation techniques to ensure prediction consistency and increase robustness against adversarial attacks. We evaluate our experiments on two offensive/hate-speech datasets and demonstrate that (i) self-training consistently improves performance regardless of model size, resulting in up to +1.5% F1-macro on both datasets, and (ii) noisy self-training with textual data augmentations, despite being successfully applied in similar settings, decreases performance on offensive and hate-speech domains when compared to the default method, even with state-of-the-art augmentations such as backtranslation.
Score: 3.703767478524629
License: http://creativecommons.org/licenses/by-sa/4.0/
Abstract: Online social media is rife with offensive and hateful comments, prompting the need for their automatic detection given the sheer amount of posts created every second. Creating high-quality human-labelled datasets for this task is difficult and costly, especially because non-offensive posts are significantly more frequent than offensive ones. However, unlabelled data is abundant, easier, and cheaper to obtain. In this scenario, self-training methods, using weakly-labelled examples to increase the amount of training data, can be employed. Recent "noisy" self-training approaches incorporate data augmentation techniques to ensure prediction consistency and increase robustness against noisy data and adversarial attacks. In this paper, we experiment with default and noisy self-training using three different textual data augmentation techniques across five different pre-trained BERT architectures varying in size. We evaluate our experiments on two offensive/hate-speech datasets and demonstrate that (i) self-training consistently improves performance regardless of model size, resulting in up to +1.5% F1-macro on both datasets, and (ii) noisy self-training with textual data augmentations, despite being successfully applied in similar settings, decreases performance on offensive and hate-speech domains when compared to the default method, even with state-of-the-art augmentations such as backtranslation.