Improving factual consistency in abstractive summarization has been a focus of current research. One promising approach is the post-editing method. However, previous works have yet to make sufficient use of factual factors in summaries and suffers from the negative effect of the training datasets. In this paper, we first propose a novel factual error correction model FactCloze based on a conditional-generation cloze task. FactCloze can construct the causality among factual factors while being able to determine whether the blank can be answered or not. Then, we propose a data distillation method to generate a more faithful summarization dataset SummDSC via multiple-dimensional evaluation. We experimentally validate the effectiveness of our approach, which leads to an improvement in multiple factual consistency metrics compared to baselines.

翻译：在抽象式摘要中提升事实一致性是当前研究的一个重点。后编辑方法是一种有前景的途径。然而，以往的工作未能充分利用摘要中的事实因素，且受到训练数据集负面效应的影响。本文首先提出一种基于条件生成填空任务的新型事实错误纠正模型FactCloze。FactCloze能够构建事实因素之间的因果关系，同时判断空白是否可被回答。随后，我们提出一种数据蒸馏方法，通过多维度评估生成更忠实于原意的摘要数据集SummDSC。实验验证了本方法的有效性，与基线相比，该方法在多个事实一致性指标上均有所提升。