Unsupervised extractive summarization aims to extract salient sentences from a document as the summary without labeled data. Recent literatures mostly research how to leverage sentence similarity to rank sentences in the order of salience. However, sentence similarity estimation using pre-trained language models mostly takes little account of document-level information and has a weak correlation with sentence salience ranking. In this paper, we proposed two novel strategies to improve sentence similarity estimation for unsupervised extractive summarization. We use contrastive learning to optimize a document-level objective that sentences from the same document are more similar than those from different documents. Moreover, we use mutual learning to enhance the relationship between sentence similarity estimation and sentence salience ranking, where an extra signal amplifier is used to refine the pivotal information. Experimental results demonstrate the effectiveness of our strategies.
翻译:未经监督的抽取摘要旨在从一份文件中提取突出的句子,作为没有标签数据的摘要。最近的文献大多研究如何利用刑罚与按显著顺序排列的刑期相似性。然而,使用经过培训的语文模型的类似性估算大多很少考虑到文件级别的信息,与判刑显著顺序的对比性关系不大。在本文中,我们提出了两项新颖战略,以改进未经监督的抽取摘要的类似性估算。我们利用对比性学习优化文件级别目标,即同一文件的量刑与不同文件的量刑更为相似。此外,我们利用相互学习加强判决相似性估算和判刑显著排序之间的关系,在其中使用额外的信号放大器改进关键信息。实验结果显示了我们战略的有效性。</s>