基于文本结构和图卷积网络的生成式摘要

目前主流的生成式自动文摘采用基于编码器—解码器架构的机器学习模型,且通常使用基于循环神经网络的编码器.该编码器主要学习文本的序列化信息,对文本的结构化信息学习能力较差.从语言学的角度来讲,文本的结构化信息对文本重要内容的判断具有重要作用.为了使编码器能够获取文本的结构信息,该文提出了基于文本结构信息的编码器,其使用了图...

Abstractive Summarization Using Text Structure and Graph Convolution Network

The current method of abstractive summarization generally adopt machine learning models based on encoder-decoder architecture, with recurrent neural network as the encoder often. To capture the structure information of the text which is believed to play an important role in judging the important content, this paper proposes a text structure information encoder via graph convolutional neural network. This paper designs a normalization and fusion layer, which aims to enable the model to model both the linear and the structure information in the text. In addition, a multi-headed attention decoder is adopted to improve the quality of the generated summary. The experimental results show that the proposed method significantly improves the system performance according to ROUGE evaluation.