The rise in hateful and offensive language directed at other users is one of the adverse side effects of the increased use of social networking platforms. This could make it difficult for human moderators to review tagged comments filtered by classification systems. To help address this issue, we present the ViHOS (Vietnamese Hate and Offensive Spans) dataset, the first human-annotated corpus containing 26k spans on 11k comments. We also provide definitions of hateful and offensive spans in Vietnamese comments as well as detailed annotation guidelines. Besides, we conduct experiments with various state-of-the-art models. Specifically, XLM-R$_{Large}$ achieved the best F1-scores in Single span detection and All spans detection, while PhoBERT$_{Large}$ obtained the highest in Multiple spans detection. Finally, our error analysis demonstrates the difficulties in detecting specific types of spans in our data for future research. Disclaimer: This paper contains real comments that could be considered profane, offensive, or abusive.

翻译：社交网络平台使用量的增长导致用户间仇恨与攻击性语言泛滥，这是其负面影响之一。这类语言使得人工审核员难以有效审查经分类系统过滤的标记评论。为解决此问题，我们提出了ViHOS（越南语仇恨与攻击性片段）数据集——首个包含11,000条评论中26,000个片段的人工标注语料库。我们提供了越南语评论中仇恨与攻击性片段的定义及详细标注指南。此外，我们基于多种先进模型进行了实验。具体而言，XLM-R$_{Large}$在单片段检测和全片段检测中取得最佳F1分数，而PhoBERT$_{Large}$在多片段检测中表现最优。最后，误差分析揭示了当前数据中特定类型片段检测的难点，为未来研究指明方向。声明：本文包含可能被视为粗俗、攻击性或侮辱性的真实评论。