RELATION EXTRACTION METHOD OF CHINESE MEDICAL TEXT BASED ON RSIG-LSTM, 1-12.

Songpu Li, Ruxin Gong, Xiaosheng Yu, and Jiaheng Li

References

  1. [1] T. Xie, J.A. Yang, and H. Liu, Chinese entity relation extractionbased on multi-feature BERT model, Computer Systems andApplications, 30(5), 2021, 253–261.
  2. [2] B. Priyankar, S. Srinivasan, W.C. Sleeman, J. Palta, R. Kapoor,and P. Ghosh, A survey on recent named entity recognitionand relationship extraction techniques on clinical texts, AppliedSciences, 11(8), 2021, 8319.
  3. [3] General Office of the State Council, Guidance of theGeneral Office of the State Council on promotingFigure 11. The time cost of six models.and standardizing the application and development ofhealth data, https://www.gov.cn/zhengce/content/2016-06/24/content 5085091.htm (accessed Oct. 2022).
  4. [4] J.H. Hu, W.Q. Zhao, and A. Fang, Research on clinical textprocessing and knowledge discovery method based on medicalbig data, China Digital Medicine, 15(7), 2020, 13–25.
  5. [5] J.S. Zhao, Q.M. Zhu, and G.D. Zhou, Review of researchin automatic keyword extraction, Journal of Software, 28(9),2017, 2431–2449.
  6. [6] Y.Q. Cao, W.P. Sheng, and H.X. Zhou, Research on newskeyword extraction based on TF-IDF-MP algorithm, Journalof East China Jiaotong University, 38(1), 2021, 122–130.
  7. [7] C. Miao, Z. Cao, and Y.C. Tam, Keyword-attentive deepsemantic matching, 2020, arXiv:2003.11516 (accessed Mar.2021).
  8. [8] X.P. Wu, Q. Zhang, F. Zhao, and L. Jiao, Entity relationextraction method for guidelines of cardiovascular disease basedon bidirectional encoder representation from transformers,Journal of Computer Applications, 41(1), 2021, 145.
  9. [9] S. Kiliarslan and M. Celik, RSigELU: A nonlinear activationfunction for deep neural networks, Expert Systems WithApplications, 174, 2021, 114805.
  10. [10] T. Mikolov, I. Sutskever, and K. Chen, Distributed represen-tations of words and phrases and their compositionality, 2013,arXiv:1310.4546v1 (accessed Oct. 2021).
  11. [11] P.J. Guan and C.P Cao, Clincal text entity relationshipextraction based on BiLSTM, Computer Engineering andSoftware, 5(1), 2019, 159–62.
  12. [12] Z. Peng, S. Wei, and J. Tian, Attention-based bidirectional longshort-term memory networks for relation classification, Proc. ofthe 54th Annual Meeting of the Association for ComputationalLinguistics, Berlin, 2016, 207–212.11
  13. [13] X.J. Zhu, H.L. Li, and J.S. Zhou, An improved attention-basedLSTM feature selection model, Journal of Beijing Institute ofMachinery, 33(122), 2018, 57–62.
  14. [14] Q.V. Le, N. Jaitly, and G.E. Hinton, A simple way toinitialize recurrent networks of rectified linear units, 2015,arXiv:1504.00941 (accessed Apr. 2022).
  15. [15] D.A. Clevert, T. Unterthiner, and S. Hochreiter, Fastand accurate deep network learning by exponential linearunits(ELUs), 2015, arXiv:1511.07289 (accessed Feb. 2022).
  16. [16] L. Qian and S. Furber, Noisy softplus: A biology inspiredactivation function, in Proc. International Conf. on NeuralInformation Processing, Neural Information Processing, Kyoto,2016, 405–412.
  17. [17] P. Ramachandran, B. Zoph, and Q.V. Le, Searching foractivation functions, 2017, arXiv:1710.05941 (accessed Oct.2021).
  18. [18] X.Z. Ye, F.F. Tao, and R.Z. Qi, Inprovement on activationfunctions of recurrent neural network architectures, Computerand Modernization, 2016, 29–33.
  19. [19] B.J. Xu and F.F. Xu, Optimization of activation function inneural network based on ArcReLU function, Journal of DataAcquisition and Processing, 34(3), 2019, 517–529.
  20. [20] F.F. Xu and B.J. Xu, Research on matching resumes andposition based on Arc-LSTM, Journal of Shangdong University(Natural Science), 56(1), 2021, 83–90.
  21. [21] O. Frunza and D. Inkpen, Extraction of disease-treatmentsemantic relations from biomedical sentences, Proc. of the2010 Workshop on Biomedical Natural Language Processing,Stroudsburg, PA, 2010, 91–98.
  22. [22] S.K. Sahu, A. Anand, and K. Oruganty, Relation extractionfrom clinical texts using domain invariant convolutional neuralnetwork, Proc. of the 15th Workshop on Biomedical NaturalLanguage Processing, Berlin, 2016, 206–215.
  23. [23] C. Zhang, X. Cheng, J. He, and G. Liu, Automatic recognitionof adhesion states using an extreme learning machine,International Journal of Robotics and Automation, 32(2), 2017,194–200.
  24. [24] Y. Zhang, H. Lin, and Z. Yang, J. Wang, S. Zhang, Y.Sun, and L. Yang, A hybrid model based on neural networksfor biomedical relation extraction, Journal of BiomedicalInformatics, 81, 2018, 83–92.
  25. [25] Z.C. Zhang, T. Zhou, R.F. Zhang, and M.Y. Zhang, Medicalentity relation recognition combining bidirectional GRU andattention, Computer Engineering, 46(514), 2020, 302–308.
  26. [26] J. Devlin, M.W. Chang, and K. Lee, BERT: Pre-training ofdeep bidirectional transformers for language understanding,2019, arXiv:1810.04805v2 (accessed May 2022).
  27. [27] W. Zhang, S. Jiang, and S. Zhao, A BERT-BiLSTM-CRF modelfor Chinese electronic medical records named entity recognition,Proc. 12th International Conf. on Intelligent ComputationTechnology and Automation (ICICTA), Xiangtan, 2019,166–169.
  28. [28] Y. Hui, L. Du, S. Lin, Y. Qu, and D. Cao, Extraction andclassification of TCM medical records based on BERT andBi-LSTM with attention mechanism, Proc. IEEE InternationalConf. on Bioinformatics and Biomedicine (BIBM), Seoul,2020, 1626–1631.
  29. [29] S. Hochreiter and J. Schmidhuber, Long short-term memory,CNeural Computation, 9(8), 1997, 1735–1780.
  30. [30] J. Su, GPlinker: Entity-relation joint extraction based onGlobalPointer, 2022, https://kexue.fm/archives/8373 (accessedMay 2022).
  31. [31] J. Liang, Q. He, D. Zhang, and S. Fan, Extraction of jointentity and relationships with soft pruning and GlobalPointer,Applied Sciences, 12(13), 2022, 6361.
  32. [32] A. Doni and T. Sasipraba, Lstm-RNN based approach forprediction of dengue cases in India, Ing´enierie des Syst`emesd’Information, 25(3), 2020, 327–335.
  33. [33] X.Q. Ji, Short term electricity price forecasting based on deeplearning in electricity market, (Beijing: North China ElectricPower University, 2019).
  34. [34] S. Eger, P. Youssef, and I. Gurevych, Is it time to swish?Comparing deep learning activation functions across NLP tasks,2019, arXiv:1901.02671v1 (accessed Jan. 2022).

Important Links:

Go Back