Multiplex Graph Neural Network for Extractive Text Summarization
Multiplex Graph Neural Network for Extractive Text Summarization
复制标题
DOI：
10.18653/v1/2021.emnlp-main.11
复制
发表时间：
2021-08
期刊：
影响因子：
--
通讯作者：
Baoyu Jing;Zeyu You;Tao Yang;Wei Fan;Hanghang Tong
中科院分区：
文献类型：
--
作者：
Baoyu Jing;Zeyu You;Tao Yang;Wei Fan;Hanghang Tong
提取文本摘要旨在从给定文档中提取最具代表性的句子作为其摘要。为了从长文本文档中提取出好的摘要，句子嵌入起着重要的作用。最近的研究利用图神经网络来捕获文档中的句子间关系（例如，话语图）来学习上下文句子嵌入。然而，这些方法既没有考虑多种类型的句间关系（例如，语义相似性和自然连接关系），也没有对句内关系（例如，单词之间的语义相似性和句法关系）进行建模。为了解决这些问题，我们提出了一种新颖的多重图卷积网络（Multi-GCN）来联合建模句子和单词之间不同类型的关系。基于Multi-GCN，我们提出了一种用于提取文本摘要的多重图摘要（Multi-GraS）模型。最后，我们在 CNN/DailyMail 基准数据集上评估所提出的模型，以证明我们方法的有效性。
Extractive text summarization aims at extracting the most representative sentences from a given document as its summary. To extract a good summary from a long text document, sentence embedding plays an important role. Recent studies have leveraged graph neural networks to capture the inter-sentential relationship (e.g., the discourse graph) within the documents to learn contextual sentence embedding. However, those approaches neither consider multiple types of inter-sentential relationships (e.g., semantic similarity and natural connection relationships), nor model intra-sentential relationships (e.g, semantic similarity and syntactic relationship among words). To address these problems, we propose a novel Multiplex Graph Convolutional Network (Multi-GCN) to jointly model different types of relationships among sentences and words. Based on Multi-GCN, we propose a Multiplex Graph Summarization (Multi-GraS) model for extractive text summarization. Finally, we evaluate the proposed models on the CNN/DailyMail benchmark dataset to demonstrate effectiveness of our method.