arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2305.02637cs.CLcs.AIcs.CY
收藏

面向跨数据集弱监督仇恨言论分类

Towards Weakly-Supervised Hate Speech Classification Across Datasets

Pompeu Fabra University(庞培法布拉大学);Catalan Institute for Research and Advanced Studies(加泰罗尼亚研究与高级研究院);Knorex(诺瑞克斯公司)

Yiping Jin, Leo Wanner, Vishakha Laxman Kadam, Alexander Shvets

AI总结:

针对仇恨言论识别中数据标注不一致导致模型泛化差的问题,提出仅用类别名的极弱监督方法,验证了其在跨数据集上的有效性,并深入分析了泛化差的根源。

摘要:

正如多位学者所指出的,当前仇恨言论(HS)识别研究的特点是数据创建策略缺乏系统性和标注模式存在分歧。因此,监督学习模型往往难以泛化到其未训练过的数据集,且在不同HS分类体系标注的数据集上训练的模型性能无法进行比较。为缓解这一问题,我们提出应用仅依赖类别名称而非标注数据中类别样本的极弱监督方法。我们展示了最先进的弱监督文本分类模型在各种数据集内和跨数据集设置中的有效性。此外,我们对HS分类模型泛化能力差的根源进行了深入的定量和定性分析。

英文摘要:

As pointed out by several scholars, current research on hate speech (HS) recognition is characterized by unsystematic data creation strategies and diverging annotation schemata. Subsequently, supervised-learning models tend to generalize poorly to datasets they were not trained on, and the performance of the models trained on datasets labeled using different HS taxonomies cannot be compared. To ease this problem, we propose applying extremely weak supervision that only relies on the class name rather than on class samples from the annotated data. We demonstrate the effectiveness of a state-of-the-art weakly-supervised text classification model in various in-dataset and cross-dataset settings. Furthermore, we conduct an in-depth quantitative and qualitative analysis of the source of poor generalizability of HS classification models.

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。

↑