arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2104.08392cs.CL
收藏

基于人类记忆模拟的无监督自动文摘

Unsupervised Extractive Summarization by Human Memory Simulation

School of Informatics, University of Edinburgh(爱丁堡大学信息学院);Naver Labs Europe

Ronald Cardenas, Matthias Galle, Shay B. Cohen

摘要:

摘要系统面临着识别和选择重要信息的核心挑战。在本文中,我们解决的问题,在无监督的提取摘要的长,结构化的文件的内容选择。我们介绍了一个广泛的知识,利用内容单元的认知表征,以及这些是如何保留或遗忘在人类记忆中。我们发现,人类记忆的这些表征的属性可以被利用来捕获科学文章中的内容单元的相关性。实验表明,我们提出的语义学在利用认知结构和文档的组织(即,文章的部分),并且自动和人工评估提供了强有力的证据,表明这些启发式方法提取了更有摘要价值的内容单元。

英文摘要:

Summarization systems face the core challenge of identifying and selecting important information. In this paper, we tackle the problem of content selection in unsupervised extractive summarization of long, structured documents. We introduce a wide range of heuristics that leverage cognitive representations of content units and how these are retained or forgotten in human memory. We find that properties of these representations of human memory can be exploited to capture relevance of content units in scientific articles. Experiments show that our proposed heuristics are effective at leveraging cognitive structures and the organization of the document (i.e.\ sections of an article), and automatic and human evaluations provide strong evidence that these heuristics extract more summary-worthy content units.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑