A Legal Approach to Hate Speech: Operationalizing the EU's Legal Framework against the Expression of Hatred as an NLP Task
Max Planck Institute for Research on Collective Goods（马克斯·普朗克集体物品研究所）；Waseda Institute for Advanced Study, Waseda University（早稻田大学高等研究所）；University of Duisburg-Essen（杜伊斯堡-埃森大学）
Frederike Zufall, Marius Hamacher, Katharina Kloppenborg, Torsten Zesch
We propose a 'legal approach' to hate speech detection by operationalization of the decision as to whether a post is subject to criminal law into an NLP task. Comparing existing regulatory regimes for hate speech, we base our investigation on the European Union's framework as it provides a widely applicable legal minimum standard. Accurately judging whether a post is punishable or not usually requires legal training. We show that, by breaking the legal assessment down into a series of simpler sub-decisions, even laypersons can annotate consistently. Based on a newly annotated dataset, our experiments show that directly learning an automated model of punishable content is challenging. However, learning the two sub-tasks of `target group' and `targeting conduct' instead of an end-to-end approach to punishability yields better results. Overall, our method also provides decisions that are more transparent than those of end-to-end models, which is a crucial point in legal decision-making.
Ceasing hate withMoH: Hate Speech Detection in Hindi-English Code-Switched Language
Optum Global Advantage（Optum 全球优势公司）；Adobe Inc.（Adobe 公司）；Delhi Technological University（德里理工大学）
社交媒体已成为人们在世界各地表达意见的基石。由于匿名功能带来更大的自由感，因此可以在网上无视社交礼仪并攻击他人而不会面临严重后果，从而不可避免地传播仇恨言论。目前筛选在线内容和抵消仇恨传播的措施还不够。造成这种情况的一个因素是社交媒体中流行的区域语言和缺乏语言灵活的仇恨言论检测器。拟议的工作重点是分析印度语-英语代码转换语言中的仇恨言论。我们的方法探讨了转换技术，以捕捉精确的文本表示。为了包含数据的结构，但与现有的算法一起使用，我们开发了MoH或Map Only Hindi，这在印地语中意味着“爱”。MoH管道包括语言识别，使用罗马印地语单词的知识库将罗马语音译为梵文印地语。最后，它采用了微调的多语言BERT和MuRIL语言模型。我们对三个数据集进行了几次定量实验研究，并使用精度，召回率和F1指标评估了性能。第一个实验研究了MoH映射文本与经典机器学习模型的性能，并显示F1分数平均增加了13%。第二个测试将所提出的工作的分数与基准模型的分数进行比较，结果显示性能提高了6%。最后，第三达到建议的MoH技术与各种数据模拟使用现有的音译库。在这方面，卫生部的表现比其他部门高出15%。我们的研究结果表明，所有三个数据集的最新得分都有显着提高。
Predicting Hate Intensity of Twitter Conversation Threads
Hohai University（河海大学）；IIIT Delhi（德里英迪拉·甘地信息技术学院）；Singapore University of Technology and Design（新加坡科技设计大学）；Indian Institute of Technology Delhi（印度理工学院德里分校）
Conditioning Large Language Models on Legal Systems? Detecting Punishable Hate Speech
Central Office for Information Technology in the Security Sector (ZITiS)（安全领域信息技术中央办公室（ZITiS））；Computational Linguistics, CATALPA, FernUniversität in Hagen（计算语言学、CATALPA、费尔本大学）；Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院）；Waseda Institute for Advanced Study, Waseda University（早稻田大学高级研究机构）
