Abstract
Span-based methods have unique advantages for solving nested named entity recognition (NER) problems. As primary information, boundaries play a crucial role in span representation. However, auxiliary information, which assists in identifying entities, still needs to be adequately investigated. In this work, We propose a simple yet effective method to enhance classification performance using boundaries and auxiliary information. Our model mainly consists of an adaptive convolution layer, an information-aware layer, and an information-agnostic layer. Adaptive convolution layers dynamically acquire words at different distances to enhance position-aware head and tail representations of spans. Information-aware and information-agnostic layers selectively incorporate boundaries and auxiliary information into the span representation and maintain boundary-oriented. Experiments show that our method outperforms the previous span-based methods and achieves state-of-the-art \(F_{1}\) scores on four NER datasets named ACE2005, ACE2004, Weibo and Resume. Experiments also show comparable results on GENIA and CoNLL2003.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cao, H., et al.: OneEE: a one-stage framework for fast overlapping and nested event extraction. In: Proceedings of COLING, pp. 1953–1964. International Committee on Computational Linguistics, Gyeongju, Republic of Korea (2022)
Cordonnier, J.B., Loukas, A., Jaggi, M.: On the relationship between self-attention and convolutional layers. arXiv preprint arXiv:1911.03584 (2019)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL, pp. 4171–4186. Association for Computational Linguistics, Minneapolis, Minnesota (2019)
Fisher, J., Vlachos, A.: Merge and label: a novel neural network architecture for nested NER. In: Proceedings of ACL, pp. 5840–5850. Association for Computational Linguistics, Florence, Italy (2019)
Gillick, D., Brunk, C., Vinyals, O., Subramanya, A.: Multilingual language processing from bytes. In: Proceedings of NAACL, pp. 1296–1306. Association for Computational Linguistics, San Diego, California (2016)
Gu, Y., Qu, X., Wang, Z., Zheng, Y., Huai, B., Yuan, N.J.: Delving deep into regularity: A simple but effective method for Chinese named entity recognition. In: Findings of NAACL, pp. 1863–1873. Association for Computational Linguistics, Seattle, United States (2022)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Huang, P., Zhao, X., Hu, M., Fang, Y., Li, X., Xiao, W.: Extract-select: a span selection framework for nested named entity recognition with generative adversarial training. In: Findings of ACL, pp. 85–96. Association for Computational Linguistics, Dublin, Ireland (2022)
Ju, M., Miwa, M., Ananiadou, S.: A neural layered model for nested named entity recognition. In: Proceedings of NAACL, pp. 1446–1459. Association for Computational Linguistics, New Orleans, Louisiana (2018)
Li, F., Lin, Z., Zhang, M., Ji, D.: A span-based model for joint overlapped and discontinuous named entity recognition. In: Proceedings of ACL-IJCNLP, pp. 4814–4828. Association for Computational Linguistics, Online (2021)
Li, J., et al.: Unified named entity recognition as word-word relation classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 10965–10973 (2022)
Li, X., Yan, H., Qiu, X., Huang, X.: FLAT: Chinese NER using flat-lattice transformer. In: Proceedings of ACL, pp. 6836–6842. Association for Computational Linguistics, Online (2020)
Li, X., Feng, J., Meng, Y., Han, Q., Wu, F., Li, J.: A unified MRC framework for named entity recognition. In: Proceedings of ACL, pp. 5849–5859. Association for Computational Linguistics, Online (2020)
Lu, W., Roth, D.: Joint mention extraction and classification with mention hypergraphs. In: Proceedings of EMNLP, pp. 857–867. Association for Computational Linguistics, Lisbon, Portugal (2015)
Ma, R., Peng, M., Zhang, Q., Wei, Z., Huang, X.: Simplify the usage of lexicon in Chinese NER. In: Proceedings of ACL, pp. 5951–5960. Association for Computational Linguistics, Online (2020)
Muis, A.O., Lu, W.: Learning to recognize discontiguous entities. In: Proceedings of EMNLP, pp. 75–84. Association for Computational Linguistics, Austin, Texas (2016)
Muis, A.O., Lu, W.: Labeling gaps between words: recognizing overlapping mentions with mention separators. In: Proceedings of EMNLP, pp. 2608–2618. Association for Computational Linguistics, Copenhagen, Denmark (2017)
Nie, Y., Tian, Y., Song, Y., Ao, X., Wan, X.: Improving named entity recognition with attentive ensemble of syntactic information. In: Findings of EMNLP, pp. 4231–4245. Association for Computational Linguistics, Online (2020)
Shen, Y., Ma, X., Tan, Z., Zhang, S., Wang, W., Lu, W.: Locate and label: a two-stage identifier for nested named entity recognition. In: Proceedings of ACL-IJCNLP, pp. 2782–2794. Association for Computational Linguistics, Online (2021)
Su, J., Lu, Y., Pan, S., Wen, B., Liu, Y.: Roformer: enhanced transformer with rotary position embedding. arXiv preprint arXiv:2104.09864 (2021)
Sun, Y., et al.: Circle loss: a unified perspective of pair similarity optimization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6398–6407 (2020)
Wang, B., Lu, W.: Neural segmental hypergraphs for overlapping mention recognition. In: Proceedings of EMNLP, pp. 204–214. Association for Computational Linguistics, Brussels, Belgium (2018)
Wang, J., Shou, L., Chen, K., Chen, G.: Pyramid: a layered model for nested named entity recognition. In: Proceedings of ACL, pp. 5918–5928. Association for Computational Linguistics, Online (2020)
Wang, X., et al.: Automated concatenation of embeddings for structured prediction. In: Proceedings of ACL-IJCNLP, pp. 2643–2660. Association for Computational Linguistics, Online (2021)
Wang, X., et al.: Improving named entity recognition by external context retrieving and cooperative learning. In: Proceedings of ACL, pp. 1800–1812. Association for Computational Linguistics, Online (2021)
Wang, Y., Yu, B., Zhu, H., Liu, T., Yu, N., Sun, L.: Discontinuous named entity recognition as maximal clique discovery. In: Proceedings ACL-IJCNLP, pp. 764–774. Association for Computational Linguistics, Online (2021)
Xu, Y., Huang, H., Feng, C., Hu, Y.: A supervised multi-head self-attention network for nested named entity recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 14185–14193 (2021)
Yan, H., Deng, B., Li, X., Qiu, X.: Tener: adapting transformer encoder for named entity recognition. arXiv preprint arXiv:1911.04474 (2019)
Yan, H., Gui, T., Dai, J., Guo, Q., Zhang, Z., Qiu, X.: A unified generative framework for various NER subtasks. In: Proceedings of ACL-IJCNLP, pp. 5808–5822. Association for Computational Linguistics, Online (2021)
Yan, H., Sun, Y., Li, X., Qiu, X.: An embarrassingly easy but strong baseline for nested named entity recognition. arXiv preprint arXiv:2208.04534 (2022), https://arxiv.53yu.com/pdf/2208.04534
Yu, J., Bohnet, B., Poesio, M.: Named entity recognition as dependency parsing. In: Proceedings of ACL, pp. 6470–6476. Association for Computational Linguistics, Online (2020)
Yuan, Z., Tan, C., Huang, S., Huang, F.: Fusing heterogeneous factors with triaffine mechanism for nested named entity recognition. In: Findings of ACL, pp. 3174–3186. Association for Computational Linguistics, Dublin, Ireland (2022)
Zhang, S., Cheng, H., Gao, J., Poon, H.: Optimizing bi-encoder for named entity recognition via contrastive learning. arXiv preprint arXiv:2208.14565 (2022)
Zhang, Y., Yang, J.: Chinese NER using lattice LSTM. In: Proceedings of ACL, pp. 1554–1564. Association for Computational Linguistics, Melbourne, Australia (2018)
Zhu, E., Li, J.: Boundary smoothing for named entity recognition. In: Proceedings of ACL, pp. 7096–7108. Association for Computational Linguistics, Dublin, Ireland (2022)
Acknowledgement
This work was supported by the Jilin Provincial Department of Education Science and Technology Research Planning Project, Grant number jjkh20220779kj. Jilin Provincial Science and Technology Development Plan Project, Grant number 20220201149gx.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sun, Y., Li, C., Kong, W. (2023). Auxiliary Information Enhanced Span-Based Model for Nested Named Entity Recognition. In: Liu, F., Duan, N., Xu, Q., Hong, Y. (eds) Natural Language Processing and Chinese Computing. NLPCC 2023. Lecture Notes in Computer Science(), vol 14302. Springer, Cham. https://doi.org/10.1007/978-3-031-44693-1_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-44693-1_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44692-4
Online ISBN: 978-3-031-44693-1
eBook Packages: Computer ScienceComputer Science (R0)