Augmented Abstractive Summarization With Document-LevelSemantic Graph

Abstract

Previous abstractive methods apply sequence-to-sequence structures to generate summary without a module to assist the system to detect vital mentions and relationships within a document. To address this problem, we utilize semantic graph to boost the generation performance. Firstly, we extract important entities from each document and then establish a graph inspired by the idea of distant supervision \citep{mintz-etal-2009-distant}. Then, we combine a Bi-LSTM with a graph encoder to obtain the representation of each graph node. A novel neural decoder is presented to leverage the information of such entity graphs. Automatic and human evaluations show the effectiveness of our technique.

arXiv commentAccepted to Journal of Data Science

References in corpus (8)

• A Deep Reinforced Model for Abstractive Summarization
• REALM: Retrieval-Augmented Language Model Pre-Training
• Text Summarization with Pretrained Encoders
• Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting
• Text Generation from Knowledge Graphs with Graph Transformers
• Robust Neural Abstractive Summarization Systems and Evaluation against Adversarial Information
• Structural Neural Encoders for AMR-to-text Generation
• An Entity-Driven Framework for Abstractive Summarization