We propose a novel, attention-based self-supervised approach to identify "claim-worthy" sentences in a fake news article, an important first step in automated fact-checking. We leverage "aboutness" of headline and content using attention mechanism for this task. The identified claims can be used for downstream task of claim verification for which we are releasing a benchmark dataset of manually selected compelling articles with veracity labels and associated evidence. This work goes beyond stylistic analysis to identifying content that influences reader belief. Experiments with three datasets show the strength of our model. Data and code available at https://github.com/architapathak/Self-Supervised-ClaimIdentification

翻译：我们提出一种新的、以关注为基础的自我监督办法,在假新闻文章中确定“符合索赔要求”的句子,这是自动核对事实的重要第一步。我们利用关注机制来利用头条和内容的“状况”来进行这项工作。已查明的索赔可以用于下游的索赔核实任务,为此,我们正在发布一组由人工挑选的具有真实性标签和相关证据的有说服力的物品的基准数据集。这项工作不仅局限于对影响读者信仰的内容进行理论分析。与三个数据集进行的实验显示了我们的模型的强度。数据和代码见https://github.com/architapathak/self-Supervised-ServicationIdationation。