Abstract
As pictographs, Chinese characters contain latent glyph information, which is often overlooked. In this paper, we propose the FGN (https://githup.com/AidenHuen/FGN-NER), Fusion Glyph Network for Chinese NER. Except for encoding glyph information with a novel CNN, this method may extract interactive information between character distributed representation and glyph representation by a fusion mechanism. The major innovations of FGN include: (1) a novel CNN structure called CGS-CNN is proposed to capture glyph information and interactive information between the neighboring graphs. (2) we provide a method with sliding window and attention mechanism to fuse the BERT representation and glyph representation for each character. This method may capture potential interactive knowledge between context and glyph. Experiments are conducted on four NER datasets, showing that FGN with LSTM-CRF as tagger achieves new state-of-the-art performance for Chinese NER. Further, more experiments are conducted to investigate the influences of various components and settings in FGN.
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
Yanan, L., Yue, Z., Dong-Hong, J.: Multi-prototype Chinese character embedding. In: Conference on Language Resources and Evaluation, pp. 855–859 (2016)
Yuxian, M., Wei, W., Fei, W., et al.: Glyce:Glyph-vectors for Chinese character representations. In: Advances in Neural Information Processing Systems, pp. 2742–2753 (2019)
Haibo, L., Masato, H., Qi, L., Heng, J.: Comparison of the impact of word segmentation on name tagging for Chinese and Japanese. In: International Conference on Language Resources and Evaluation, pp. 2532–2536 (2014)
Liu, Z., Zhu, C., Zhao, T.: Chinese named entity recognition with a sequence labeling approach: based on characters, or based on words? In: Huang, D.S., Zhang, X., Reyes GarcÃa, C.A., Zhang, L. (eds.) ICIC 2010. LNCS (LNAI), vol. 6216, pp. 634–640. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-14932-0_78
Jacob, D., Ming-Wei, C., Kenton, L., Kristina, T.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Conference of the North American Chapter of the Association for Computational Linguistics, pp. 4171–4186 (2019)
Xuezhe, M., Eduard, H.: End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp. 1064–1074 (2016)
Sun, Y., Lin, L., Yang, N., Ji, Z., Wang, X.: Radical-enhanced Chinese character embedding. In: Loo, C.K., Yap, K.S., Wong, K.W., Teoh, A., Huang, K. (eds.) ICONIP 2014. LNCS, vol. 8835, pp. 279–286. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-12640-1_34
Falcon, D., Cai, Z.: Glyph-aware embedding of chinese characters. In: Proceedings of the First Workshop on Subword and Character Level Models in NLP, pp. 64–69 (2017)
Yan, S., Christian, H., Jorg, T., Joakim, N.: Character-based joint segmentation and pos tagging for chinese using bidirectional rnn-crf. arXiv preprint arXiv:1704.01314, Computer Science (2017)
Ashish, V., Noam, S., Niki, P., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)
Arijit, S., Chan, S.: Using Chinese glyphs for named entity recognition. arXiv preprint arXiv:1909.09922, Computer Science (2019)
Qi, Z,, Jinlan, F., Xiaoyu, L., Xuanjing, H.: Adaptive co-attention network for named entity recognition in tweets. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 5674–5681 (2018)
Jianfei, Y., Jing, J.: Adapting BERT for target-oriented multimodal sentiment classification. In: Proceedings of the International Joint Conference on Artificial Intelligence, pp. 5408–5414 (2019)
Sijie, M., Haifeng, H., Songlong, X.: Divide, Conquer And Combine: Hierarchical Feature Fusion Network With Local And Global Perspectives For Multimodal Affective Computing. In: Annual Meeting of the Association for Computational Linguistics, pp. 481–492 (2019)
Ronan, C., Jason, W., Leon, B., et al.: Natural language processing (almost) from scratch. J. Mach. Learn. Res. 12(Aug), 2493–2537 (2011)
Huang, Z., Xu, W., Yu, K.: Bidirectional LSTM-CRF models for sequence tagging. arXiv preprint arXiv: 1508.01991, Computer Science (2015)
Dai, Z., Fei, H., Li, P.: Coreference aware representation learning for neural named entity recognition. In: Proceedings of the International Joint Conference on Artificial Intelligence, pp. 4946–4953 (2019)
Dong, C., Zhang, J., Zong, C., Hattori, M., Di, H.: Character-based LSTM-CRF with radical-level features for chinese named entity recognition. In: Lin, C.-Y., Xue, N., Zhao, D.-Y., Huang, X., Feng, Y. (eds.) ICCPOL/NLPCC -2016. LNCS (LNAI), vol. 10102, pp. 239–250. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-50496-4_20
Yue, Z., Jie, Y.: Chinese NER using lattice LSTM. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp.1554–1564 (2018)
Wei, L., Tongge, X., Qinghua, X.: An encoding strategy based word-character LSTM for Chinese NER. In: Proceedings of Conference of the North American Chapter of the Association for Computational Linguistics, pp. 2379–2389 (2019)
Shuiwang, J., Wei, X., Ming, Y., et al.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221–231 (2012)
Ralph, W., Sameer, P., Lance, R., et al.: Ontonotes release 4.0. LDC2011T03, Philadelphia, Penn.: Linguistic Data Consortium (2011)
Gina-Anne, L.: 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)
Nanyun, P., Mark, D.: Named entity recognition for chinese social media with jointly trained embeddings. In: Conference on Empirical Methods in Natural Language Processing, pp. 548–554 (2015)
Su, T., Hungyi, L.: Learning Chinese word representations from glyphs of characters. preprint arXiv:1708.04755, Computer Science (2017)
Acknowledgments
This work was supported by the National Natural Science Foundation of China (No. 61572145) and the Major Projects of Guangdong Education Department for Foundation Research and Applied Research (No. 2017KZDXM031). The authors would like to thank the anonymous reviewers for their valuable comments and suggestions.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Xuan, Z., Bao, R., Jiang, S. (2021). FGN: Fusion Glyph Network for Chinese Named Entity Recognition. In: Chen, H., Liu, K., Sun, Y., Wang, S., Hou, L. (eds) Knowledge Graph and Semantic Computing: Knowledge Graph and Cognitive Intelligence. CCKS 2020. Communications in Computer and Information Science, vol 1356. Springer, Singapore. https://doi.org/10.1007/978-981-16-1964-9_3
Download citation
DOI: https://doi.org/10.1007/978-981-16-1964-9_3
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-1963-2
Online ISBN: 978-981-16-1964-9
eBook Packages: Computer ScienceComputer Science (R0)