Graph-based Neural Multi-Document Summarization

Abstract

We propose a neural multi-document summarization (MDS) system that incorporates sentence relation graphs. We employ a Graph Convolutional Network (GCN) on the relation graphs, with sentence embeddings obtained from Recurrent Neural Networks as input node features. Through multiple layer-wise propagation, the GCN generates high-level hidden sentence features for salience estimation. We then use a greedy heuristic to extract salient sentences while avoiding redundancy. In our experiments on DUC 2004, we consider three types of sentence relation graphs and demonstrate the advantage of combining sentence relations in graphs with the representation power of deep neural networks. Our model improves upon traditional graph-based extractive approaches and the vanilla GRU sequence model with no graph, and it achieves competitive results against other state-of-the-art multi-document summarization systems.

In CoNLL 2017

References in corpus (2)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents

Cited by in corpus (8)

• Heterogeneous Graph Neural Networks for Extractive Document Summarization
• PoBRL: Optimizing Multi-Document Summarization by Blending Reinforcement Learning Policies
• Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs
• Dating Documents using Graph Convolution Networks
• Centrality Meets Centroid: A Graph-based Approach for Unsupervised Document Summarization
• Ranking sentences from product description & bullets for better search
• Graph-of-Tweets: A Graph Merging Approach to Sub-event Identification
• Timestamping Documents and Beliefs