ABSTRACT
As a crucial first step in the process of constructing knowledge graph, the accuracy of named entity recognition determines the construction effect of the final graph. However, at present, Chinese named entity recognition methods still have many problems, such as long training time and lower accuracy. Hence, we come up with a BERT-BILSTM-ACRF entity recognition method that combines the “self-attention” mechanism. To begin with, Bert model is selected as the embedding layer, the text is vectorized, and the character position in-formation is obtained through the bidirectional Long Short-Term Memory network. Secondly, the internal relationship of the character sequence is further searched through the self-attention mechanism, and finally the final optimal sequence is decoded by the conditional random field model. To check the effectiveness of the BERT-BILSTM-ACRF model, the model is applied to the data set of the university course textbook” Da-ta Structure”, and the result reaches 98.97%F1 value and 98.14%accuracy, which has good experimental results and certain practical value.
- J. Li, A. Sun, “A survey on deep learning for named entity recognition,” Journal of Transactions on Knowledge and Data Engineering, vol. 34, no. 1, pp. 50-70, 2020.Google ScholarDigital Library
- X. Liu, H. Chen, W. Xia, “Overview of named entity recognition,” Journal of Contemporary Educational Research, vol. 6, no. 5, pp. 65-68, 2022.Google ScholarCross Ref
- N. Yasuda, S.-i. Takagi, A. Toriumi, Spectral shape analysis of infrared absorption of thermally grown silicon dioxide films, Applied Surface Science 117-118(1997) 216-220.Google ScholarCross Ref
- E. Tome, B.-K Seljak, and P. Koroˇsec, “A rule-based named-entity recognition method for knowledge extraction of evidence-based dietary recommendations,” PloS one, vol. 12, no. 6, e0179488, 2017.Google Scholar
- P.-J. Gorinski, H.-H. Wu, C. Grover, R. Tobin, and C. Talbot, “Named Entity Recognition for Electronic Health Records: A Comparison of Rule-based and Machine Learning Approaches,” arXiv preprint, 2019. [Online]. Available: https://doi.org/10.48550/arXiv.1903.03985.Google ScholarCross Ref
- S.-J Ren, “Research on Named Entity Recognition of Drug Instructions Based on Conditional Random Fields,” Journal of Yangtze River Information and Communication, vol. 34, no. 10, pp. 232-234, 2021.Google Scholar
- K. Hakala, S. Pyysalo, “Biomedical named entity recognition with multilingual BERT,” in fifth workshop on BioNLP open shared tasks. IEEE, 2019, pp. 56–61.Google ScholarCross Ref
- C. Liang, Y. Yu, H -M. Jiang, S. Er, R -J. Wang, T. Zhao, “BOND: BERT-Assisted Open-Domain Named Entity Recognition with Distant Supervision,” in twenty-sixth ACM SIGKDD international conference on knowledge discovery & data mining. IEEE, 2020, pp. 1054–1064.Google Scholar
- Phopli W , Maliyaem M , Haruechaiyasak C ,et al.Microblog Entity Detection for Natural Disaster Management[J].Journal of Advances in Information Technology, 2021.DOI:10.12720/jait.12.4.351-356.Google ScholarCross Ref
- Y.-Y Zhu, G.-X Wang, and B.-F Karlsson, “CAN-NER: Convolutional Attention Network for Chinese Named Entity Recognition,” arXiv preprint, 2020. [Online]. Available: https://doi.org/10.48550/arXiv.1904.02141.Google ScholarCross Ref
- L. Tenney, D. Das, E.Pavlick “BERT rediscovers the classical NLP pipeline,” arXiv preprint, 2019. [Online]. Available: https://doi.org/10.48550/arXiv.1905.05950.Google ScholarCross Ref
- H. Choi, J. Kim, S -Joe. “Evaluation of bert and albert sentence embedding performance on downstream nlp,” in 2020 25th International conference on pattern recognition (ICPR). IEEE, 2021, pp. 5482–5487.Google ScholarCross Ref
- A -A. Aziz, M -N. Tihami, M -S. Islam. “A deep recurrent neural network with bilstm model for sentiment classification,” in 2018 International conference on Bangla speech and language processing (ICBSLP). IEEE, 2018, pp. 1–4.Google ScholarCross Ref
- Z. Hameed, B -G. Zapirain, F. She “Research on Named Entity Recognition of Chinese Electronic Medical Records Based on CNN-CRF,” Journal of Ieee Access, vol. 8, no. 1, pp. 73992-74001, 2020. Journal article with page number.Google ScholarCross Ref
- W. AlKhwiter, N -A. Twairesh, “Part-of-speech tagging for Arabic tweets using CRF and Bi-LSTM,” Journal of Computer Speech Language, vol. 65, no. 1, pp. 101138, 2021.Google ScholarCross Ref
- L -H. Lee, C -H. Lu, T -M. Lin, “NCUEE-NLP at SemEval-2022 Task 11: Chinese named entity recognition using the BERT-BiLSTM-CRF model,” in Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022). IEEE, 2022, pp. 1597–1602.Google ScholarCross Ref
- Z -Y. Niu, G -Q. Zhong, H. Yu, “A review on the attention mechanism of deep learning,” Journal of Neurocomputing, vol. 452, no. 1, pp. 48-62, 2021.Google ScholarCross Ref
Index Terms
- Named Entities Based on the BERT-BILSTM-ACRF Model Recognition Research
Recommendations
Inducing Gazetteer for Chinese Named Entity Recognition Based on Local High-Frequent Strings
FITME '09: Proceedings of the 2009 Second International Conference on Future Information Technology and Management EngineeringGazetteers, or entity dictionaries, are important for named entity recognition (NER). Although the dictionaries extracted automatically by the previous methods from a corpus, web or Wikipedia are very huge, they also misses some entities, especially the ...
Named entity recognition and resolution in legal text
Semantic Processing of Legal TextsNamed entities in text are persons, places, companies, etc. that are explicitly mentioned in text using proper nouns. The process of finding named entities in a text and classifying them to a semantic type, is called named entity recognition. Resolution ...
Chinese mineral named entity recognition based on BERT model
AbstractMineral named entity recognition (MNER) is the extraction for the specific types of entities from unstructured Chinese mineral text, which is a prerequisite for building a mineral knowledge graph. MNER can also provide important data ...
Highlights- Present a BERT-based model for Chinese mineral named entity recognition.
- ...
Comments