Abstract
As one of the most common and effective techniques for obtaining information, relation extraction is a key task in machine learning. Understanding the current development status of computer technology, we know that the technical methods of extracting information mainly rely on a large number of manual operation and processing features, and with the full promotion of neural networks, it provides a new perspective for actual relationship extraction and data generation. Therefore, on the basis of understanding the current relationship extraction and data generation methods, this paper conducts an empirical analysis of the Chinese character relationship extraction method with convolutional neural network as the core and designs and proposes a Chinese character relationship extraction system scheme based on the convolutional neural network model. Using the convolutional neural network model to automatically obtain features and classify the relationship between the characters mastered, the actual accuracy rate can reach 92.87%, and the average recall rate can reach 86.92%. The final result proves that the relationship extraction data generation method based on neural network has unique application advantages.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Zhang, S.L., Pan, J.F., Han, Z.Z., Qiu, R.S., Zhao, J.: Incomplete LFM signal recognition method based on BP neural network. Electron. Inform. Warfare Technol. 36(05), 59–62+106 (2021)
Qi, Q.K., Wang, W.L.: Research on data literacy evaluation of university graduate students based on data life cycle. Inform. Sci. 39(09), 125–130+145 (2021). https://doi.org/10.13833/j.issn.1007-7634.2021.09.017
Cao, Y.D., Liu, H.Y., Jia, X., Li, X.H.: Overview of image quality evaluation methods based on deep learning. Comput. Eng. Appl. 1–11 (2021). http://kns-cnki-net--bjmu.bjmu.exiazai.vip:8001/kcms/detail/11.2127.TP.20210827.1430.002.html
Qi, F.: On-line assessment of power system transient stability based on one-dimensional convolutional neural network. Sichuan Electr. Power Technol. 44(04), 38–42+89 (2021). https://doi.org/10.16527/j.issn.1003-6954.20210408
Guo, Z.P., Zhang, Q.G.: Research on CNN-BiGRU-CRF network Chinese word segmentation based on combined dictionary. Electron. Des. Eng. 29(16), 64–69+74(2021). https://doi.org/10.14022/j.issn1674-6236.2021.16.014
Shi, H., Liu, R.F., Liu, X.Y., Chen, H.Y.: Question generation model based on article and near-answer sentence information. Chin. J. Inform. 35(08), 127–134 (2021)
He, P., Sun, F., He, X.F., Lin, Y.P., Duan, S.K.: Optimization of laser cutting process parameter prediction model for small samples. Laser Mag. 1–7 (2021). http://kns-cnki-net--bjmu.bjmu.exiazai.vip:8001/kcms/detail/50.1085.TN.20210723.1736.016.html
Gao, J.Y.: Research on pedestrian recognition method based on deep network. In: Information and Computer (Theoretical Edition), vol. 33(14), pp. 47–49 (2021)
Wu, Y.F., Zhang, Y.S.: Survey of problem generation research. Chin. J. Inform. 35(07), 1–9 (2021)
Wang, R.H.: Research and implementation of user behavior feature extraction and identity association methods in multi-source heterogeneous social networks. Bei**g University of Posts and Telecommunications (2021)
Holena, M.: Piecewise-linear neural networks and their relationship to rule extraction from data. Neural Comput. 18(11), 2813–2853 (2006)
Alguliev, R.M., Aliguliyev, R.M., Isazade, N.R.: DESAMC+DocSum: differential evolution with self-adaptive mutation and crossover parameters for multi-document summarization. Knowl.-Based Syst. 36, 21–38 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Gao, G., Li, T. (2023). Data Generation Method and Training Mode of Relationship Extraction Based on Neural Network. In: Kountchev, R., Nakamatsu, K., Wang, W., Kountcheva, R. (eds) Proceedings of the World Conference on Intelligent and 3-D Technologies (WCI3DT 2022). Smart Innovation, Systems and Technologies, vol 323. Springer, Singapore. https://doi.org/10.1007/978-981-19-7184-6_19
Download citation
DOI: https://doi.org/10.1007/978-981-19-7184-6_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-7183-9
Online ISBN: 978-981-19-7184-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)