Compressed Heterogeneous Graph for Abstractive Multi-Document Summarization

Multi-document summarization (MDS) aims to generate a summary for a number of related documents. We propose HGSum — an MDS model that extends an encoder-decoder architecture to incorporate a heterogeneous graph to represent different semantic units (e.g., words and sentences) of the documents. This contrasts with existing MDS models which do not consider different edge types of graphs and as such do not capture the diversity of relationships in the documents. To preserve only key information and relationships of the documents in the heterogeneous graph, HGSum uses graph pooling to compress the input graph. And to guide HGSum to learn the compression, we introduce an additional objective that maximizes the similarity between the compressed graph and the graph constructed from the ground-truth summary during training. HGSum is trained end-to-end with the graph similarity and standard cross-entropy objectives. Experimental results over Multi-News, WCEP-100, and Arxiv show that HGSum outperforms state-of-the-art MDS models. The code for our model and experiments is available at: https://github.com/oaimli/HGSum.

Authors

• Miao Li Key Laboratory of Intelligent Perception and Human-Machine Collaboration, ShanghaiTech University
• Jianzhong Qi The University of Melbourne
• Jey Han Lau School of Computing and Information Systems, The University of Melbourne

Keywords

• ML: Graph-based Machine Learning
• ML: Transfer, Domain Adaptation, Multi-Task Learning
• SNLP: Generation
• SNLP: Summarization