abstractive summarization is the process of generating a summary given a
document as input. Although significant progress has been made, the factual
inconsistency between the document and the generated summary still limits its
practical applications. Previous work found that the probab
文章提出了一种基于事实感知的自动摘要模型 FASum,通过图注意力来提取和整合摘要生成过程中的事实关系,并设计了一个名为 FC 的事实校正模型来自动纠正现有系统生成摘要中的事实错误。实证结果表明,基于事实感知的自动摘要可以生成具有更高事实一致性的抽象摘要,并且纠错模型通过只修改少量关键词就可以提高给定摘要的事实一致性。