Abstract
As a basic work of natural language processing (NLP), named entity recognition (NER) has attracted wide attention. Many methods of fusing the potential word representations in a Chinese sentence into the corresponding Chinese character representations have been applied to the Long-Short Term Memory (LSTM) model with good results in the Chinese NER task. However, the structure of LSTM cannot take full advantage of the parallelism of GPUs. Hence, we design a character-word attention adapter in the embedding layer to accelerate information fusion. Recently, the Transformer encoder has been popular in NLP for its parallel computing performance and the advantage of modeling the long-distance context. Nevertheless, the native Transformer encoder performs poorly on the NER task. We have deeply analyzed some of the shortcomings of the Transformer encoder. On these bases, we have further refined the position embedding and the self-attention calculation method in the Transformer encoder. Finally, we propose a new architecture of Chinese NER using the improved Transformer encoder and the lexicon adapter. On the four datasets of the Chinese NER task, our model achieves better performance than other models.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Che, W., Wang, M., Manning, C.D., Liu, T.: Named entity recognition with bilingual constraints. In: Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 52–62 (2013)
Chen, A., Peng, F., Shan, R., Sun, G.: Chinese named entity recognition with conditional probabilistic models. In: Proceedings of the Fifth SIGHAN Workshop on Chinese Language Processing, pp. 173–176 (2006)
Chen, Y., Xu, L., Liu, K., Zeng, D., Zhao, J.: Event extraction via dynamic multi-pooling convolutional neural networks. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 167–176 (2015)
Gui, T., Ma, R., Zhang, Q., Zhao, L., Jiang, Y.G., Huang, X.: CNN-based Chinese NER with lexicon rethinking. In: IJCAI, pp. 4982–4988 (2019)
He, H., Sun, X.: F-score driven max margin neural network for named entity recognition in Chinese social media. In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pp. 713–718 (2017)
He, H., Sun, X.: A unified model for cross-domain and semi-supervised named entity recognition in Chinese social media. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31 (2017)
Levow, G.A.: The third international Chinese language processing bakeoff: word segmentation and named entity recognition. In: Proceedings of the Fifth SIGHAN Workshop on Chinese Language Processing, pp. 108–117 (2006)
Li, X., Yan, H., Qiu, X., Huang, X.: Flat: Chinese NER using flat-lattice transformer. arXiv preprint arXiv:2004.11795 (2020)
Lin, Y., Shen, S., Liu, Z., Luan, H., Sun, M.: Neural relation extraction with selective attention over instances. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2124–2133 (2016)
Lu, Y., Zhang, Y., Ji, D.: Multi-prototype Chinese character embedding. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), pp. 855–859 (2016)
Peng, M., Ma, R., Zhang, Q., Huang, X.: Simplify the usage of lexicon in Chinese NER. In: ACL (2020)
Peng, N., Dredze, M.: Named entity recognition for Chinese social media with jointly trained embeddings. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 548–554 (2015)
Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp. 3104–3112 (2014)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)
Weischedel, R., et al.: Ontonotes release 4.0. LDC2011T03. Linguistic Data Consortium, Philadelphia (2011)
Wu, P., Zhang, X., Feng, Z.: A survey of question answering over knowledge base. In: Zhu, X., Qin, B., Zhu, X., Liu, M., Qian, L. (eds.) CCKS 2019. CCIS, vol. 1134, pp. 86–97. Springer, Singapore (2019). https://doi.org/10.1007/978-981-15-1956-7_8
Yan, H., Deng, B., Li, X., Qiu, X.: Tener: adapting transformer encoder for named entity recognition. arXiv preprint arXiv:1911.04474 (2019)
Yang, J., Teng, Z., Zhang, M., Zhang, Y.: Combining discrete and neural features for sequence labeling. In: Gelbukh, A. (ed.) CICLing 2016. LNCS, vol. 9623, pp. 140–154. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-75477-2_9
Zhang, D., Chi, C., Zhan, X.: Leveraging lexical features for Chinese named entity recognition via static and dynamic weighting. IAENG Int. J. Comput. Sci. 48(1) (2021)
Zhang, Y., Yang, J.: Chinese NER using lattice LSTM (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sun, M., Wang, L., Sheng, T., He, Z., Huang, Y. (2022). Chinese Named Entity Recognition Using the Improved Transformer Encoder and the Lexicon Adapter. In: Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., Aydin, M. (eds) Artificial Neural Networks and Machine Learning – ICANN 2022. ICANN 2022. Lecture Notes in Computer Science, vol 13530. Springer, Cham. https://doi.org/10.1007/978-3-031-15931-2_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-15931-2_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-15930-5
Online ISBN: 978-3-031-15931-2
eBook Packages: Computer ScienceComputer Science (R0)