正确性
自动汇总
计算机科学
人工智能
自然语言处理
图形
知识图
计算
理论计算机科学
情报检索
算法
作者
Chenguang Zhu,William Hinthorn,Ruochen Xu,Qingkai Zeng,Michael Zeng,Xuedong Huang,Meng Jiang
出处
期刊:Cornell University - arXiv
日期:2020-03-19
被引量:18
摘要
A commonly observed problem with abstractive summarization is the distortion or fabrication of factual information in the article. This inconsistency between summary and original text has led to various concerns over its applicability. In this paper, we propose to boost factual correctness of summaries via the fusion of knowledge, i.e. extracted factual relations from the article. We present a Fact-Aware Summarization model, FASum. In this model, the knowledge information can be organically integrated into the summary generation process via neural graph computation and effectively improves the factual correctness. Empirical results show that FASum generates summaries with significantly higher factual correctness compared with state-of-the-art abstractive summarization systems, both under an independently trained factual correctness evaluator and human evaluation. For example, in CNN/DailyMail dataset, FASum obtains 1.2% higher fact correctness scores than UniLM and 4.5% higher than BottomUp.
科研通智能强力驱动
Strongly Powered by AbleSci AI