论文标题
提高抽象摘要的事实一致性
Enhancing Factual Consistency of Abstractive Summarization
论文作者
论文摘要
在本文中发现自动抽象性摘要经常扭曲或捏造事实。摘要和原始文本之间的这种不一致严重影响了其适用性。我们提出了一种事实感知的摘要模型FASUM，以通过图形注意将事实关系提取和整合到摘要生成过程中。然后，我们设计了一个事实纠正型FC，以自动从现有系统生成的摘要中纠正事实错误。经验结果表明，与现有系统相比，事实感知的摘要可以产生具有更高事实一致性的抽象摘要，而校正模型仅通过修改几个关键字来提高给定摘要的事实一致性。
Automatic abstractive summaries are found to often distort or fabricate facts in the article. This inconsistency between summary and original text has seriously impacted its applicability. We propose a fact-aware summarization model FASum to extract and integrate factual relations into the summary generation process via graph attention. We then design a factual corrector model FC to automatically correct factual errors from summaries generated by existing systems. Empirical results show that the fact-aware summarization can produce abstractive summaries with higher factual consistency compared with existing systems, and the correction model improves the factual consistency of given summaries via modifying only a few keywords.
