Graph-based Neural Multi-Document Summarization

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... (read more)

PDF Abstract CONLL 2017 PDF CONLL 2017 Abstract
No code implementations yet. Submit your code now

Datasets


  Add Datasets introduced or used in this paper
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Multi-Document Summarization DUC 2004 GCN: Personalized Discourse Graph ROUGE-1 38.23 # 1

Methods used in the Paper


METHOD TYPE
GCN
Graph Models
GRU
Recurrent Neural Networks