Affiliation:
1. School of Cyberspace Security and Computer Science, Hebei University, Baoding 071000, China
Abstract
Named entity recognition can deeply explore semantic features and enhance the ability of vector representation of text data. This paper proposes a named entity recognition method based on multi-head attention to aim at the problem of fuzzy lexical boundary in Chinese named entity recognition. Firstly, Word2vec is used to extract word vectors, HMM is used to extract boundary vectors, ALBERT is used to extract character vectors, the Feedforward-attention mechanism is used to fuse the three vectors, and then the fused vectors representation is used to remove features by BiLSTM. Then multi-head attention is used to mine the potential word information in the text features. Finally, the text label classification results are output after the conditional random field screening. Through the verification of WeiboNER, MSRA, and CLUENER2020 datasets, the results show that the proposed algorithm can effectively improve the performance of named entity recognition.
Reference33 articles.
1. Dinarelli, M., and Tellier, I. (2016). Improving Recurrent Neural Networks For Sequence Labelling. arXiv.
2. Gui, T., Ma, R., Zhang, Q., Zhao, L., Jiang, Y.-G., and Huang, X. (2019, January 10–16). CNN-Based Chinese NER with Lexicon Rethinking. Proceedings of the International Joint Conference on Artificial Intelligence IJCAI, Macao, China.
3. Hu, D., and Wei, L. (2020). SLK-NER: Exploiting second-order lexicon knowledge for Chinese NER. arXiv.
4. Jia, C., Shi, Y., and Yang, Q. (2020, January 16–20). Entity enhanced BERT pre-training for Chinese NER. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online.
5. Yan, S., Chai, J., and Wu, L. (2020, January 12–14). Bidirectional GRU with multi-head attention for Chinese NER. Proceedings of the 2020 IEEE 5th Information Technology and Mechatronics Engineering Conference (ITOEC), Chongqing, China.
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献