SAPGraph: Structure-aware extractive summarization for scientific papers with heterogeneous graph
Published in Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, 2022
This paper introduces SAPGraph, a novel approach for structure-aware extractive summarization of scientific papers using heterogeneous graph neural networks. The method leverages the structural information inherent in scientific documents to improve summarization quality.
The work demonstrates how graph-based representations can capture the complex relationships between different sections of scientific papers, leading to more coherent and informative summaries.
Recommended citation: S Qi, L Li, Y Li, J Jiang, D Hu, Y Li, Y Zhu, Y Zhou, M Litvak, N Vanetik. (2022). "SAPGraph: Structure-aware extractive summarization for scientific papers with heterogeneous graph." Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics.
Download Paper