arxiv:2604.03583

Text Summarization With Graph Attention Networks

Published on Apr 4

Authors:

Abstract

Graph information from RST and Coref structures was explored to improve summarization models, with mixed results showing that simpler MLP architectures outperformed Graph Attention Networks while a new XSum benchmark was established.

AI-generated summary

This study aimed to leverage graph information, particularly Rhetorical Structure Theory (RST) and Co-reference (Coref) graphs, to enhance the performance of our baseline summarization models. Specifically, we experimented with a Graph Attention Network architecture to incorporate graph information. However, this architecture did not enhance the performance. Subsequently, we used a simple Multi-layer Perceptron architecture, which improved the results in our proposed model on our primary dataset, CNN/DM. Additionally, we annotated XSum dataset with RST graph information, establishing a benchmark for future graph-based summarization models. This secondary dataset posed multiple challenges, revealing both the merits and limitations of our models.