Abstract
As a kind of long legal text with a fixed structure, the medical dispute judgment documents have a large amount of redundant information. The information directly harms the semantic representation of the documents and the recommendation of similar cases. Therefore, a semantic representation scheme for medical dispute judgment documents based on elements extraction is proposed in this paper. The scheme consists of two stages. In the first stage, key sentences and keywords are extracted from the original documents based on BERT+FC model and BERT+CRF model to filter the redundant information. In the second stage, text matching training and mask training based on specific keywords are carried out according to the extracted elements, and the BERT model is transferred to a semantic representation model through multi-task learning. The experiment results show that the semantic representation scheme can improve the accuracy of matching medical dispute judgment documents to 85.84%.
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
Zhang, Y., Jin, R., Zhou, Z.H.: Understanding bag-of-words model: a statistical framework. Int. J. Mach. Learn. Cybern. 1(1–4), 43–52 (2010)
Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. arXiv:1706.03762 (2017)
Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Proceedings of Annual Conference on Neural Information Processing Systems, Montreal, Quebec, Canada, pp. 3104–3112 (2014)
Kiros, R., Zhu, Y., Salakhutdinov, R., et al.: Skip-thought vectors. In: Proceedings Annual Conference on Neural Information Processing Systems, pp. 3294–3302, Montreal, Quebec, Canada (2015)
Lai, S., Xu, L., Liu, K., et al.: Recurrent convolutional neural networks for text classification. In: Proceedings of AAAI (2015)
Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of EMNLP, pp. 1746–1751 (2014)
Kalchbrenner, N., Grefenstette, E., Blunsom, P.: A convolutional neural network for modelling sentences. arXiv:1404.2188 (2014)
Gan, Z., Pu, Y., Henao, R.: Learning generic sentence representations using convolutional neural networks. In: Proceedings of EMNLP, pp. 2390–2400 (2017)
Devlin, J., Chang, M.W., Lee, K., et al.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805 (2018)
Lan, Z., Chen, M., Goodman, S., et al.: ALBERT: a lite BERT for self-supervised learning of language representations. In: Proceedings of ICLR, Addis Ababa, Ethiopia (2020)
Joshi, M., Chen, D., Liu, Y.: SpanBERT: improving pre-training by representing and predicting spans. Trans. Assoc. Comput. Linguistics 8, 64–77 (2020)
Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using siamese BERT- networks. In: Proceedings of EMNLP-IJCNLP, pp. 3980–3990 (2019)
J Su, J., Cao, J., Liu, W., et al.: Whitening sentence representations for better semantics and faster retrieval. arXiv:2103.15316 (2021)
Kumar, S., Sastry, H.G., Marriboyina, V., Alshazly, H., Idris, S.A.: Semantic information extraction from multi-corpora using deep learning. Comput. Mater. Continua 70(3), 5021–5038 (2022)
Liu, D., Zhang, L., Shao, Y., Sun, J.: Leverage external knowledge and self-attention for Chinese semantic dependency graph parsing. Intell. Autom. Soft Comput. 28(2), 447–458 (2021)
Jamil, S., Noor, S., Ahmed, I., Gohar, N.: F: Semantic modeling of events using linked open data. Intell. Autom. Soft Comput. 29(2), 511–524 (2021)
Hu, S., Li, X., Deng, Y., Peng, Y., Lin, B.: A semantic supervision method for abstractive summarization. Comput. Mater. Continua 69(1), 145–158 (2021)
Liu, H.S., Jun, G., Zheng, Y.Y.: Chinese named entity recognition model based on BERT. In: MATEC Web of Conferences, vol. 336, pp. 6021–6021 (2021)
Cheng, J., Liu, J., Xu, X., Xia, D., Liu, L., Sheng, V.: A review of Chinese named entity recognition. KSII Trans. Internet Inf. Syst. 15(6) (2012)
Niwattanakul, S., Singthongchai, J., Naenudorn, E.: Using of Jaccard coefficient for key-words similarity. In: Proceedings of the International Multi Conference of Engineers and Computer Scientists, pp. 380–384 (2013)
Bromley, J., Guyon, I., Lecun, Y.: Signature verification using a ‘siamese’ time delay neural network. In: Advances in Neural Information Processing Systems 6, pp. 737–744 (1993)
Su, J.L.: Hierarchical decomposition position encoding allows BERT to handle very long text. https://kexue.fm/archives/7947 (2020)
Acknowledgement
This work was partly supported by the National Key R&D Program of China (2018YFC0830200), the Fundamental Research Funds for the Central Universities (2242018S30021 and 2242017S30023) and Open Research Fund from Key Laboratory of Computer Network and Information Integration in Southeast University, Ministry of Education, China.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
An, S., Wang, T., Wang, L., Zhong, M., Zhang, B. (2022). A Semantic Representation Scheme for Medical Dispute Judgment Documents Based on Elements Extraction. In: Sun, X., Zhang, X., Xia, Z., Bertino, E. (eds) Artificial Intelligence and Security. ICAIS 2022. Lecture Notes in Computer Science, vol 13339. Springer, Cham. https://doi.org/10.1007/978-3-031-06788-4_34
Download citation
DOI: https://doi.org/10.1007/978-3-031-06788-4_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-06787-7
Online ISBN: 978-3-031-06788-4
eBook Packages: Computer ScienceComputer Science (R0)