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 (6)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents
• Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
• Neural Summarization by Extracting Sentences and Words
• AttSum: Joint Learning of Focusing and Summarization with Neural Attention
• Neural Network-Based Abstract Generation for Opinions and Arguments

Cited by in corpus (18)

• Attention-based Clinical Note Summarization
• Heterogeneous Graph Neural Networks for Extractive Document Summarization
• A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss
• Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization
• PoBRL: Optimizing Multi-Document Summarization by Blending Reinforcement Learning Policies
• PoinT-5: Pointer Network and T-5 based Financial NarrativeSummarisation
• Latent Semantic Analysis Approach for Document Summarization Based on Word Embeddings
• Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs
• Automatic Text Extractive Summarization Based on Graph and Pre-trained Language Model Attention
• Dating Documents using Graph Convolution Networks
• Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervised
• A Novel ILP Framework for Summarizing Content with High Lexical Variety
• A Comprehensive Attempt to Research Statement Generation
• Centrality Meets Centroid: A Graph-based Approach for Unsupervised Document Summarization
• Graph-of-Tweets: A Graph Merging Approach to Sub-event Identification
• Timestamping Documents and Beliefs
• Ranking sentences from product description & bullets for better search
• Learning Syntactic and Dynamic Selective Encoding for Document Summarization