用于攻击性和仇恨言论检测任务的带数据增强的噪声自训练
Noisy Self-Training with Data Augmentations for Offensive and Hate Speech Detection Tasks
AI总结：
本文研究了在五种不同规模的预训练BERT架构上结合三种文本数据增强的默认与噪声自训练方法，发现自训练能稳定提升攻击性和仇恨言论检测性能（F1-macro最高提升1.5%），但噪声自训练反而会降低该领域性能。
摘要：
在线社交媒体充斥着攻击性和仇恨性评论，鉴于每秒产生的帖子数量巨大，迫切需要对其进行自动检测。为该任务创建高质量的人工标注数据集既困难又昂贵，特别是因为非攻击性帖子比攻击性帖子多得多。然而，未标注数据丰富、更容易且更便宜地获取。在这种情况下，可以采用自训练方法，使用弱标注样本来增加训练数据量。最近的“噪声”自训练方法结合了数据增强技术，以确保预测一致性并增强对噪声数据和对抗性攻击的鲁棒性。在本文中，我们使用三种不同的文本数据增强技术，在大小不同的五种预训练 BERT 架构上，进行了默认和噪声自训练实验。我们在两个攻击性/仇恨言论数据集上评估了实验，并证明：(i) 无论模型大小如何，自训练都能持续提高性能，在两个数据集上 F1-macro 最高提升 +1.5%；(ii) 带有文本数据增强的噪声自训练，尽管在类似环境中成功应用过，但与默认方法相比，在攻击性和仇恨言论领域会降低性能，即使使用如回译等最先进的增强技术也是如此。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
