Text Summarization With Graph Attention Networks

Mohammadreza Ardestani, Yllias Chali
Proceedings of The 4th NeurIPS Efficient Natural Language and Speech Processing Workshop, PMLR 262:540-553, 2024.

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 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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v262-ardestani24a, title = {Text Summarization With Graph Attention Networks}, author = {Ardestani, Mohammadreza and Chali, Yllias}, booktitle = {Proceedings of The 4th NeurIPS Efficient Natural Language and Speech Processing Workshop}, pages = {540--553}, year = {2024}, editor = {Rezagholizadeh, Mehdi and Passban, Peyman and Samiee, Soheila and Partovi Nia, Vahid and Cheng, Yu and Deng, Yue and Liu, Qun and Chen, Boxing}, volume = {262}, series = {Proceedings of Machine Learning Research}, month = {14 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v262/main/assets/ardestani24a/ardestani24a.pdf}, url = {https://proceedings.mlr.press/v262/ardestani24a.html}, 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 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.} }
Endnote
%0 Conference Paper %T Text Summarization With Graph Attention Networks %A Mohammadreza Ardestani %A Yllias Chali %B Proceedings of The 4th NeurIPS Efficient Natural Language and Speech Processing Workshop %C Proceedings of Machine Learning Research %D 2024 %E Mehdi Rezagholizadeh %E Peyman Passban %E Soheila Samiee %E Vahid Partovi Nia %E Yu Cheng %E Yue Deng %E Qun Liu %E Boxing Chen %F pmlr-v262-ardestani24a %I PMLR %P 540--553 %U https://proceedings.mlr.press/v262/ardestani24a.html %V 262 %X 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.
APA
Ardestani, M. & Chali, Y.. (2024). Text Summarization With Graph Attention Networks. Proceedings of The 4th NeurIPS Efficient Natural Language and Speech Processing Workshop, in Proceedings of Machine Learning Research 262:540-553 Available from https://proceedings.mlr.press/v262/ardestani24a.html.

Related Material