跨数据集弱监督仇恨言论分类（英文版）

英文标题：Towards Weakly-Supervised Hate Speech Classification Across Datasets中文摘要：本篇论文提出了一种基于极弱监督策略的方法以解决仅存在于部分数据集的种族主义言辞（HS）的识别问题，并探究了 HS 分类模型泛化能力不佳的原因。英文摘要：As pointed out by several scholars, current research on hate speech (HS)recognition is characterized by unsystematic data creation strategies anddiverging annotation schemata. Subsequently, supervised-learning models tend togeneralize poorly to datasets they were not trained on, and the performance ofthe models trained on datasets labeled using