Abstract
With the advancement of digitalization in the medical field, electronic medical data has gradually gathered for the exploration of intelligent diagnosing. In particular, electronic medical record (EMR) summarization techniques can help doctors carry out diagnosis and treatment services more effectively, thus presenting substantial practical value. However, we point out there lacks investigation and dedicated designs for Chinese EMRs summarization. In this paper, by studying the characteristics of Chinese EMRs, we propose a novel summarization model MCMS by combining multi-granularity heterogeneous graphs and graph attention networks. The model can further capture potential information in Chinese EMRs by constructing a heterogeneous graph structure of words, basic chapter units, and sentences. We construct a Chinese EMR dataset and validate the proposed model on it. Experimental results show that our model outperforms the state-of-the-art summarization models.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhao, S., Hu, M., Cai, Z., Chen, H., Liu, F.: Dynamic modeling cross-and self-lattice attention network for Chinese ner. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 14515–14523 (2021)
Zhao, S., Hu, M., Cai, Z., Liu, F.: Modeling dense cross-modal interactions for joint entity-relation extraction. In: IJCAI, pp. 4032–4038 (2020)
Dernoncourt, F., Lee, J.Y., Szolovits, P.: Neural networks for joint sentence classification in medical paper abstracts. In: EACL (2017)
Erkan, G., Radev, D.R.: Lexrank: graph-based lexical centrality as salience in text summarization. J. Artif. Intell. Res. 22, 457–479 (2004)
Kipf, T., Welling, M.: Semi-supervised classification with graph convolutional networks (2017). ArXiv abs/1609.02907
Mihalcea, R., Tarau, P.: TextRank: bringing order into text. In: EMNLP, pp. 404–411 (2004)
See, A., Liu, P.J., Manning, C.D.: Get to the point: summarization with pointer-generator networks. In: ACL, pp. 1073–1083 (2017)
Ševa, J., Wackerbauer, M., Leser, U.: Identifying key sentences for precision oncology using semi-supervised learning. In: Proceedings of the BioNLP 2018 Workshop, pp. 35–46 (2018)
Song, Y., Tian, Y., Wang, N., Xia, F.: Summarizing medical conversations via identifying important utterances. In: COLING, pp. 717–729 (2020)
Wang, D., Liu, P., Zhong, M., Fu, J., Qiu, X., Huang, X.: Exploring domain shift in extractive text summarization (2019). ArXiv abs/1908.11664
Wang, D., Liu, P., Zheng, Y., Qiu, X., Huang, X.: Heterogeneous graph neural networks for extractive document summarization (2020). ArXiv abs/2004.12393
Xu, J., Durrett, G.: Neural extractive text summarization with syntactic compression. In: EMNLP/IJCNLP, pp. 3292–3303. ACL, Hong Kong (2019)
Zhao, S., Hu, M., Cai, Z., Zhang, Z., Zhou, T., Liu, F.: Enhancing chinese character representation with lattice-aligned attention. IEEE Trans. Neural Netw. Learn. Syst., 1–10 (2021). https://doi.org/10.1109/TNNLS.2021.3114378
Acknowledgments
This work is supported by the National Key Research and Development Program of China (2020YFC2003400).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Luo, R., Wang, Y., Zhao, S., Zhou, T., Cai, Z. (2021). Leveraging Multi-granularity Heterogeneous Graph for Chinese Electronic Medical Records Summarization. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Communications in Computer and Information Science, vol 1516. Springer, Cham. https://doi.org/10.1007/978-3-030-92307-5_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-92307-5_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92306-8
Online ISBN: 978-3-030-92307-5
eBook Packages: Computer ScienceComputer Science (R0)