arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2208.04489cs.CL
收藏

基于HateXplain和BERT的仇恨语音检测

Exploring Hate Speech Detection with HateXplain and BERT

Carnegie Mellon University(卡内基梅隆大学)

Arvind Subramaniam, Aryan Mehra, Sayani Kundu

摘要:

仇恨言论以多种形式针对社区进行贬损性评论,并使人类在社会进步中后退一步。HateXplain是最近发布的第一个数据集,它以基本原理的形式使用注释的跨度,以及语音分类类别和目标社区,使分类更人性化,可解释,准确和更少偏见。我们调整BERT以理由和类别预测的形式执行此任务,并比较我们在准确性、可解释性和偏差等不同指标上的表现。我们的创新有三个方面。首先,我们实验了具有不同重要性值的合并的基本类丢失。其次,我们广泛地实验了基本原理的地面真理注意力值。通过引入保守和宽松的注意力,我们比较了模型在HateXplain上的性能,并验证了我们的假设。第三,为了改善我们模型中的非预期偏见,我们使用了目标社区词的掩蔽,并注意到偏见和可解释性指标的改善。总的来说,我们成功地实现了模型的可扩展性,偏差消除和几个增量改进的原始BERT实现。

英文摘要:

Hate Speech takes many forms to target communities with derogatory comments, and takes humanity a step back in societal progress. HateXplain is a recently published and first dataset to use annotated spans in the form of rationales, along with speech classification categories and targeted communities to make the classification more humanlike, explainable, accurate and less biased. We tune BERT to perform this task in the form of rationales and class prediction, and compare our performance on different metrics spanning across accuracy, explainability and bias. Our novelty is threefold. Firstly, we experiment with the amalgamated rationale class loss with different importance values. Secondly, we experiment extensively with the ground truth attention values for the rationales. With the introduction of conservative and lenient attentions, we compare performance of the model on HateXplain and test our hypothesis. Thirdly, in order to improve the unintended bias in our models, we use masking of the target community words and note the improvement in bias and explainability metrics. Overall, we are successful in achieving model explanability, bias removal and several incremental improvements on the original BERT implementation.

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。

↑