A study of text summarization with graph attention networks
No Thumbnail Available
Date
2024
Authors
Ardestani, Mohammadreza
University of Lethbridge. Faculty of Arts and Science
Journal Title
Journal ISSN
Volume Title
Publisher
Lethbridge, Alta. : University of Lethbridge, Dept. of Mathematics and Computer Science
Abstract
This study aimed to leverage graph information, particularly Rhetorical Structure Theory (RST) and Co-reference (Coref) graphs, to enhance the performance of our baseline sum- marization models. Specifically, we experimented with a Graph Attention Network archi- tecture 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. Addition- ally, we annotated XSum dataset with RST graph information, establishing a benchmark for future graph-based summarizing models. This secondary dataset posed multiple chal- lenges, revealing both the merits and limitations of our models.
Description
Keywords
natural language processing , text summarization , graph attention networks , summarization models , stage-wise summarization model