A critical point of multi-document summarization (MDS) is to learn the relations among various documents. In this paper, we propose a novel abstractive MDS model, in which we represent multiple documents as a heterogeneous graph, taking semantic nodes of different granularities into account, and then apply a graph-to-sequence framework to generate summaries. Moreover, we employ a neural topic model to jointly discover latent topics that can act as cross-document semantic units to bridge different documents and provide global information to guide the summary generation. Since topic extraction can be viewed as a special type of summarization that "summarizes" texts into a more abstract format, i.e., a topic distribution, we adopt a multi-task learning strategy to jointly train the topic and summarization module, allowing the promotion of each other. Experimental results on the Multi-News dataset demonstrate that our model outperforms previous state-of-the-art MDS models on both Rouge metrics and human evaluation, meanwhile learns high-quality topics.
翻译:多文件总和(MDS)的关键点是学习各种文件之间的关系。 在本文中,我们提出一个新的抽象的MDS模型,在模型中我们将多个文件作为多元图解,将不同颗粒的语义节点考虑在内,然后应用一个图表到顺序的框架来生成摘要。此外,我们使用神经专题模型共同发现潜在的议题,这些议题可以作为交叉文档的语义单位来连接不同文件,并提供全球信息来指导摘要的生成。由于专题提取可以被视为一种特殊类型的总结类型,将文本“摘要”化成一种更加抽象的格式,即专题分布,我们采用多任务学习战略来联合培训主题和合成模块,从而相互促进。多新数据集的实验结果表明,我们的模型超越了以前关于红色指标和人类评估的状态的MDS模型,同时学习高质量的专题。