使用可解释的神经符号模型检测上下文不一致的多模态错误信息（英文版）

英文标题：Detecting Out-of-Context Multimodal Misinformation with interpretable neural-symbolic model中文摘要：本文提出了一种可解释的跨模态去上下文检测方法来辨别不匹配的内容和交叉模态的矛盾，可以帮助事实查核网站记录阐明批驳，实验表明该方法在保持准确率的同时能提供更多可解释的预测。英文摘要：Recent years have witnessed the sustained evolution of misinformation thataims at manipulating public opinions. Unlike traditional rumors or fake newseditors who mainly rely on generated and/or counterfeited images, text andvideos, current misinformation creators now more tend to use out-of-contextmultimedi