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.
翻译:在文章中,自动抽象摘要往往被认为歪曲或捏造事实,摘要和原始案文之间的这种不一致严重影响了其适用性。我们提议采用一个事实认知汇总模型FASum,通过图形关注提取事实关系并将其纳入摘要生成过程。然后我们设计一个事实纠正模型FC,自动纠正现有系统摘要中的事实错误。经验结果显示,事实认知汇总可产生抽象摘要,与现有系统相比,事实一致性更高,纠正模型只修改几个关键词,使特定摘要在事实上更加一致。