Due to the broad range of social media platforms and their user groups, the requirements of abusive language detection systems are varied and ever-changing. Already a large set of annotated corpora with different properties and label sets were created, such as hate or misogyny detection, but the form and targets of abusive speech are constantly changing. Since, the annotation of new corpora is expensive, in this work we leverage datasets we already have, covering a wide range of tasks related to abusive language detection, in order to build models cheaply for a new target label set and/or language, using only a few training examples of the target domain. We propose a two-step approach: first we train our model in a multitask fashion. We then carry out few-shot adaptation to the target requirements. Our experiments show that by leveraging already existing datasets and only a few-shots of the target task the performance of models can be improved not only monolingually but across languages as well. Our analysis also shows that our models acquire a general understanding of abusive language, since they improve the prediction of labels which are present only in the target dataset. We also analyze the trade-off between specializing the already existing datasets to a given target setup for best performance and its negative effects on model adaptability.

翻译：由于社交媒体平台及其用户群体的广泛性，恶意语言检测系统的需求呈现出多样性和持续变化的特点。尽管已有大量具有不同属性和标签集的注释语料库被创建（例如仇恨言论或厌女内容检测），但侮辱性言语的形式和攻击对象仍在不断演变。鉴于新语料库的注释成本高昂，本研究通过充分利用已有数据集（涵盖与恶意语言检测相关的广泛任务），仅使用目标领域的少量训练样本，即可为目标标签集和/或语言低成本构建模型。我们提出两阶段方法：首先以多任务方式训练模型，随后进行针对目标需求的少样本适配。实验表明，通过利用现有数据集及目标任务的少量样本，模型的性能不仅在单语环境下得到提升，跨语言场景亦如此。分析还显示，我们的模型建立了对恶意语言的通用理解能力，因其能改进仅存在于目标数据集中的标签预测结果。同时，我们探讨了将现有数据集特化至特定目标任务以获得最佳性能，与其对模型适应性的负面影响之间的权衡关系。