Paper Group ANR 799
Graph-based Neural Multi-Document Summarization …
Graph-based Neural Multi-Document Summarization
| Title | Graph-based Neural Multi-Document Summarization |
| Authors | Michihiro Yasunaga, Rui Zhang, Kshitijh Meelu, Ayush Pareek, Krishnan Srinivasan, Dragomir Radev |
| 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. |
| Tasks | Document Summarization, Multi-Document Summarization, Sentence Embeddings |
| Published | 2017-06-20 |
| URL | http://arxiv.org/abs/1706.06681v3 |
| http://arxiv.org/pdf/1706.06681v3.pdf | |
| PWC | https://paperswithcode.com/paper/graph-based-neural-multi-document |
| Repo | |
| Framework | |
