Abstract
As an integral part of deep learning, attention mechanism and bi-directional long short-term memory (Bi-LSTM) are widely used in the field of NLP (natural language processing) and their effectiveness has been well recognized. This paper adopts an attention-based Bi-LSTM approach to the question of Chinese NER (named entity recognition). With the use of word2vec, we compile vectorized dictionaries and employ Bi-LSTM models to train text vectors, with which the output eigenvectors of the attention model are multiplied. Finally, softmax is used to classify vectors in order to achieve Chinese NER. In four different configurations, our experiments describe the impact of the domain relevance of Chinese character vectors, phrase vectors, and vectorized datasets on the effectiveness of Chinese NER. The experimental results show that the standard precision (P), recall (R), and F1-score (F1) are 97.51%, 95.33%, and 96.41% respectively.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Xu, J.Z., Zhu, J., Zhao, R., Zhang, L., Li, J.J.: Astronautics named entity recognition based on CRF algorithm. J. Electronic Design Engineering. 25, 42–46 (2017). 1674-6236(2017)20-0042-05
Li, X., Wei, X.H., Jia, L., Chen, X., Liu, L., Zhang, Y.E.: Recognition of crops, diseases and pesticides named entities in Chinese based in conditional random fields. Trans. Chin. Soc. Agric. Mach. 48 (2017). https://doi.org/10.6041/j.issn.1000-1298.2017.S0.029
Wang, H.B., Shen, Q., Xian, Y.T.: Research on Chinese named entity recognition fusing transfer learning. J. Chin. Mini-Micro Comput. Syst. 38, 346–351 (2017). 1000-1220(2017)02-0346-06
Zhang, H.N., Wu, D.Y., Liu, Y., Cheng, X.Q.: Chinese named entity recognition based on deep neural network. J. Chin. Inf. Process. 31, 8–35 (2017). 1003-0077(2017)04-0028-08
Rocktäschel, T., Grefenstette, E., Hermann, K.M., et al.: Reasoning about entailment with neural attention. ICLR (2016). https://www.researchgate.net/publication/282181875
Wang, H., Shi, J.Z., Zhang, Z.W.: Text semantic relation of LSTM based on attention. Appl. Res. Comput. 35, 1417–1440 (2018). https://doi.org/10.3969/j.issn.1001-3695.2018.05.029
Liu, B.Y., Wu, D.Y., Liu, X.R., Cheng, X.Q.: Chinese named entity recognition incorporating global word boundary features. J. Chin. Inf. Process. 31, 86–91 (2017). 1003-0077(2017)02-0086-06
Feng, Y.H., Yu, H., Sun, G., Sun, J.J.: Named entity recognition method based on BLSTM. Comput. Sci. 45, 261–268 (2018). https://doi.org/10.11896/j.issn.1002-137X.2018.02.045
Hu, J., Zhang, J.C.: Bidirectional recurrent networks for Chinese word segmentation. J. Chin. Comput. Syst. 03, 522–526 (2017). http://xwxt.sict.ac.cn/EN/abstract/abstract3837.shtml
Guo, M.S., Zhang, Y., Liu, T.: Research advances and prospect of recognizing textual entailment and knowledge acquisition. Chin. J. Comput. 40, 889–910 (2017). https://doi.org/10.11897/SP.J.1016.2017.00889
Cao, C.Y., Lv, Q.: Using bidirectional LSTM deep neural network for protein residue contact prediction. J. Chin. Comput. Syst. 03, 531–535 (2017). http://xwxt.sict.ac.cn/EN/Y2017/V38/I3/531
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. J. Comput. Sci. (2014). https://www.researchgate.net/publication/265252627_Neural_Machine_Translation_by_Jointly_Learning_to_Align_and_Translate
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, K., Ren, W., Zhang, Y. (2018). Attention-Based Bi-LSTM for Chinese Named Entity Recognition. In: Hong, JF., Su, Q., Wu, JS. (eds) Chinese Lexical Semantics. CLSW 2018. Lecture Notes in Computer Science(), vol 11173. Springer, Cham. https://doi.org/10.1007/978-3-030-04015-4_56
Download citation
DOI: https://doi.org/10.1007/978-3-030-04015-4_56
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-04014-7
Online ISBN: 978-3-030-04015-4
eBook Packages: Computer ScienceComputer Science (R0)