Selective Attention Encoders by Syntactic Graph Convolutional Networks for Document Summarization

TL;DR

This paper introduces a novel document summarization method using syntactic graph convolutional networks with selective attention to effectively capture structural and semantic information, achieving state-of-the-art results.

Contribution

It proposes a new approach combining syntactic graph convolutional networks and selective attention for improved abstractive summarization.

Findings

Outperforms baseline models on CNN/Daily Mail dataset

Achieves state-of-the-art summarization performance

Effectively captures syntactic and semantic structures

Abstract

Abstractive text summarization is a challenging task, and one need to design a mechanism to effectively extract salient information from the source text and then generate a summary. A parsing process of the source text contains critical syntactic or semantic structures, which is useful to generate more accurate summary. However, modeling a parsing tree for text summarization is not trivial due to its non-linear structure and it is harder to deal with a document that includes multiple sentences and their parsing trees. In this paper, we propose to use a graph to connect the parsing trees from the sentences in a document and utilize the stacked graph convolutional networks (GCNs) to learn the syntactic representation for a document. The selective attention mechanism is used to extract salient information in semantic and structural aspect and generate an abstractive summary. We evaluate our approach on the CNN/Daily Mail text summarization dataset. The experimental results show that the proposed GCNs based selective attention approach outperforms the baselines and achieves the state-of-the-art performance on the dataset.