Analyzing Sentence Fusion in Abstractive Summarization
Analyzing Sentence Fusion in Abstractive Summarization
复制标题
DOI：
10.18653/v1/d19-5413
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Logan Lebanoff;John Muchovej;Franck Dernoncourt;Doo Soon Kim;Seokhwan Kim;W. Chang;Fei Liu
中科院分区：
文献类型：
--
作者：
Logan Lebanoff;John Muchovej;Franck Dernoncourt;Doo Soon Kim;Seokhwan Kim;W. Chang;Fei Liu
虽然最近在抽象摘要方面的工作已经在自动度量中获得了更高的分数，但是对这些系统如何将从多个文档句子中获取的信息联合收割机结合起来的理解很少。在本文中，我们分析了五个国家的最先进的抽象摘要器的输出，侧重于总结句子，形成句子融合。我们要求评判员对摘要句的语法性、忠实性和融合方法进行评判。我们的分析表明，系统句大多是语法，但往往不能保持忠实于原文。
While recent work in abstractive summarization has resulted in higher scores in automatic metrics, there is little understanding on how these systems combine information taken from multiple document sentences. In this paper, we analyze the outputs of five state-of-the-art abstractive summarizers, focusing on summary sentences that are formed by sentence fusion. We ask assessors to judge the grammaticality, faithfulness, and method of fusion for summary sentences. Our analysis reveals that system sentences are mostly grammatical, but often fail to remain faithful to the original article.