arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.08954cs.CLcs.IRcs.LG
收藏

SummPip:基于句子图压缩的无监督多文档摘要

SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression

Monash University(莫纳什大学);Deakin University(迪肯大学);Shandesitong

Jinming Zhao, Ming Liu, Longxiang Gao, Yuan Jin, Lan Du, He Zhao, He Zhang, Gholamreza Haffari

摘要:

获取多文档摘要(MDS)的训练数据是耗时和资源密集型的,所以最近的神经模型只能在有限的领域进行训练。在本文中,我们提出了SummPip:一种用于多文档摘要的无监督方法,在该方法中,我们将原始文档转换为句子图,同时考虑语言和深度表示,然后应用谱聚类来获得多个句子聚类,最后压缩每个聚类以生成最终摘要。在Multi-News和DUC-2004数据集上的实验表明,我们的方法与以前的无监督方法相比具有竞争力,甚至可以与神经监督方法相媲美。此外,人类的评价表明,我们的系统产生一致和完整的摘要相比,人类的书面。

英文摘要:

Obtaining training data for multi-document summarization (MDS) is time consuming and resource-intensive, so recent neural models can only be trained for limited domains. In this paper, we propose SummPip: an unsupervised method for multi-document summarization, in which we convert the original documents to a sentence graph, taking both linguistic and deep representation into account, then apply spectral clustering to obtain multiple clusters of sentences, and finally compress each cluster to generate the final summary. Experiments on Multi-News and DUC-2004 datasets show that our method is competitive to previous unsupervised methods and is even comparable to the neural supervised approaches. In addition, human evaluation shows our system produces consistent and complete summaries compared to human written ones.

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。

↑