Abstract
Named Entity Recognition (NER) is not only one of the most important directions in Natural Language Processing (NLP), but also plays an essential pre-processing role in many downstream NLP tasks. In recent years, most of the existing methods solve Chinese NER tasks by leveraging word lexicon, which have been empirically proven to be effective. However, these methods that depend on lexical knowledge too much tend to be confused by lexicon words, which leads to recognizing false entities. In addition, the lexicon is just a method to augment performance for the NER models, but cannot provide the dependency information of every Chinese word in a sentence, which causes relatively poor results in complex text. In order to solve these issues, this paper proposes a Multi-graph Collaborative Semantic Network (MCSN) fusing the dependency information of Chinese words. We build the dependency relationships of Chinese words by leveraging Graph Attention Network. With the dependency relationships of Chinese words, MCSN not only overcomes the shortages of lexicon, but also better captures the semantic information of Chinese words. Experimental results on some Chinese benchmarking datasets show that our methods are not only effective, but also outperform the state-of-the-art (SOTA) results. Especially in the Weibo-NM dataset, our methods can outperform it more than 9.34% in F1 score, in contrast with the SOTA models.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chen, H., Yin, C., Fan, X., Qiao, L., Rong, W., Xiong, Z.: Learning path recommendation for MOOC platforms based on a knowledge graph. In: KSEM, pp. 600–611 (2021)
Cheng, D., Song, H., He, X., Xu, B.: Joint entity and relation extraction for long text. In: KSEM, pp. 152–162 (2021)
Ding, R., Xie, P., Zhang, X., Lu, W., Li, L., Si, L.: A neural multi-digraph model for Chinese NER with gazetteers. In: ACL, pp. 1462–1467 (2019)
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)
Gui, T., et al.: A lexicon-based graph neural network for Chinese NER. In: EMNLP, pp. 1039–1049 (2019)
He, H., Sun, X.: F-score driven max margin neural network for named entity recognition in Chinese social media. In: EACL, pp. 713–718 (2017)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Lafferty, J.D., McCallum, A., Pereira, F.C.N.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: Proceedings of the Eighteenth International Conference on Machine Learning, pp. 282–289 (2001)
Li, Q., Huang, Z., Dou, Y., Zhang, Z.: A framework of data augmentation while active learning for Chinese named entity recognition. In: KSEM, pp. 88–100 (2021)
Li, X., Yan, H., Qiu, X., Huang, X.: FLAT: Chinese NER using flat-lattice transformer. In: ACL, pp. 6836–6842 (2020)
Liu, P., Guo, Y., Wang, F., Li, G.: Chinese named entity recognition: the state of the art. Neurocomputing 473, 37–53 (2022)
Ma, R., Peng, M., Zhang, Q., Wei, Z., Huang, X.: Simplify the usage of lexicon in Chinese NER. In: ACL, pp. 5951–5960 (2020)
Peng, N., Dredze, M.: Named entity recognition for Chinese social media with jointly trained embeddings. In: Proceedings of the EMNLP, pp. 548–554 (2015)
Pradhan, S., Ramshaw, L., Marcus, M., Palmer, M., Weischedel, R., Xue, N.: Conll-2011 shared task: modeling unrestricted coreference in ontonotes. In: Computational Natural Language Learning, pp. 1–27 (2011)
Qiu, H., Zheng, Q., Msahli, M., Memmi, G., Qiu, M., Lu, J.: Topological graph convolutional network-based urban traffic flow and density prediction. IEEE Trans. Intell. Transp. Syst. 22(7), 4560–4569 (2021)
Sui, D., Chen, Y., Liu, K., Zhao, J., Liu, S.: Leverage lexical knowledge for Chinese named entity recognition via collaborative graph network. In: EMNLP-IJCNLP, pp. 3830–3840 (2019)
Tamine, L., Goeuriot, L.: Semantic information retrieval on medical texts: research challenges, survey, and open issues. ACM Comput. Surv. 146:1–146:38 (2022)
Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. In: International Conference on Learning Representations (2018)
Viterbi, A.J.: Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. IEEE Trans. Inf. Theory 13(2), 260–269 (1967)
Wu, S., Song, X., Feng, Z.: MECT: Multi-metadata embedding based cross-transformer for Chinese named entity recognition. In: ACL-IJCNLP, pp. 1529–1539 (2021)
Yang, J., Teng, Z., Zhang, M., Zhang, Y.: Combining discrete and neural features for sequence labeling. In: International Conference on Intelligent Text Processing and Computational Linguistics, pp. 140–154 (2016)
Zhang, F., Li, R., Xu, K., Xu, H.: Similarity-based heterogeneous graph attention network for knowledge-enhanced recommendation. In: KSEM, pp. 488–499 (2021)
Zhang, Y., Gao, T., Lu, J., Cheng, Z., Xiao, G.: Adaptive entity alignment for cross-lingual knowledge graph. In: KSEM, pp. 474–487 (2021)
Zhang, Y., Yang, J.: Chinese NER using lattice LSTM. In: ACL, pp. 1554–1564 (2018)
Zhang, Z., Han, X., Liu, Z., Jiang, X., Sun, M., Liu, Q.: Ernie: enhanced language representation with informative entities. arXiv preprint arXiv:1905.07129 (2019)
Zhu, Y., Wang, G.: CAN-NER: convolutional attention network for Chinese named entity recognition. In: NAACL, pp. 3384–3393 (2019)
Acknowledgements
The works described in this paper are supported by The National Natural Science Foundation of China under Grant Nos. 61772210 and U1911201; Guangdong Province Universities Pearl River Scholar Funded Scheme (2018); The Project of Science and Technology in Guangzhou in China under Grant Nos.202007040006; Key Projects of the National Social Science Foundation of China under Grant Nos. 19ZDA041.
Author information
Authors and Affiliations
Corresponding authors
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
Zhang, Y., Gu, W., Ma, W., Jiang, Y. (2022). MCSN: Multi-graph Collaborative Semantic Network for Chinese NER. In: Memmi, G., Yang, B., Kong, L., Zhang, T., Qiu, M. (eds) Knowledge Science, Engineering and Management. KSEM 2022. Lecture Notes in Computer Science(), vol 13368. Springer, Cham. https://doi.org/10.1007/978-3-031-10983-6_25
Download citation
DOI: https://doi.org/10.1007/978-3-031-10983-6_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-10982-9
Online ISBN: 978-3-031-10983-6
eBook Packages: Computer ScienceComputer Science (R0)