Text Summarization With Graph Attention Networks
This work addresses text summarization for NLP researchers, but it is incremental as it builds on existing graph-based methods with mixed results.
The study tackled text summarization by incorporating graph information like RST and Coref graphs, but found that a Graph Attention Network did not improve performance, while a Multi-layer Perceptron did, achieving unspecified gains on the CNN/DM dataset, and they also annotated the XSum dataset to create a benchmark.
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.