Abstract
Although the current two-stage prototypical network approach based on pretrained language models has achieved success in few-shot named entity recognition (NER) tasks, the span boundary at the entity span detection stage is still difficult to locate, leading to the extraction of redundant or even incorrect entity spans, which greatly affects the subsequent entity type classification stage; moreover, how to improve the prototypical networks in the entity type classification stage so that it can better express semantic information remains a challenging issue. In this paper, we propose Label Prompt Guiding framework for two-stage few-shot NER (LPGNER), dividing the few-shot NER task into two stages: entity span detection and entity type classification. During training phase, the model is trained separately for the span detection and entity type classification stages by constructing a concise but effective prompt label template that provides additional labeling information for given samples. In the inference process, a span detector is used to extract and predict each input's entity span, then convert the input using the prompt template, and use the well-trained entity type classification model to further predict its type. The experimental results show that LPGNER improves upon baseline methods on the large-scale few-shot NER dataset FEW-NERD; at the same time, its generalizability across different domain benchmarks on cross-domain datasets has been verified.
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
Alqaaidi, S., Bozorgi, E.: A survey on recent named entity recognition and relation classification methods with focus on few-shot learning approaches (2023). arXiv preprint arXiv:2310.19055
Cao, J., Gao, Y., Huang, H.: A prototype-based few-shot named entity recognition. In: Proc. of the 8th International Conference on Computing and Artificial Intelligence, pp. 338–343. ACM (2022)
Fritzler, A., Logacheva,V., Kretov, M.: Few-shot classification in named entity recognition task. In: The 34th ACM/SIGAPP Symposium on Applied Computing, pp. 993–1000. ACM (2019)
Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Proc. of the 31st International Conference on Neural Information Processing Systems, pp. 4080–4090. ACM (2017)
Ma, T., Jiang, H., Wu, Q., et al.: Decomposed meta-learning for few-shot named entity recognition. In: Findings of the Association for Computational Linguistics, pp. 1584–1596. ACL (2022)
Khosla, P., Teterwak, P., Wang, C., et al.: Supervised contrastive learning. In: Proc. of the 34th International Conference on Neural Information Processing Systems, pp. 18661–18673. ACM (2020)
Ding, N., Xu, G., Chen, Y., et al.: Few-nerd: a few-shot named entity recognition dataset. In: Proc. of the 59th Annual Meeting of the Association for Computational Linguistics, pp. 3198–3213. ACL (2021)
Yang, Y., Katiyar, A.: Simple and effective few-shot named entity recognition with structured nearest neighbor learning. In: Proc. of the 2020 Conference on Empirical Methods in Natural Language Processing, pp. 6365–6375. ACL (2020)
Liu, P., Yuan, W., Fu, J., et al.: Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. ACM Comput. Surv. 55(9), 1–35 (2023)
Das, S., Das, S., Das, S., et al.: CONTaiNER: few-shot named entity recognition via contrastive learning. In: Proc. of the 60th Annual Meeting of the Association for Computational Linguistics, pp. 6338–6353. ACL (2021)
Huang, Y., He, K., Wang, Y., et al.: COPNER: contrastive learning with prompt guiding for few-shot named entity recognition. In: Proceedings of the 29th International Conference on Computational Linguistics, pp. 2515–2527. ACL (2022)
Wang, J., Wang, C., Tan, C., et al.: Spanproto: a two-stage span-based prototypical network for few-shot named entity recognition. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 3466–3476. ACL (2022)
Li, Y., Yu, Y., Qian, T.: Type-aware decomposed framework for few-shot named entity recognition. In: Proc. of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 8911–8927. ACL (2023)
Ma, J., Ballesteros, M., Doss, S., et al.: Label semantics for few shot named entity recognition. In: Proc. of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 1956–1971. ACL (2022)
Devlin, J., Chang, M-W., Lee, K., et al.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proc. of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4171–4186. ACL (2019)
Wang, P., Xu, R., Liu, T., et al.: An enhanced span-based decomposition method for few-shot sequence labeling. In: Proc. of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 5012–5024. ACL (2022)
Weischedel, R., et al.: Ontonotes release 4.0 LDC2011T03. Web Download. Philadelphia: Linguistic Data Consortium (2011)
Sang, E., Meulder, F.: Introduction to the CoNLL-2003 shared task: language-independent named entity recognition. In: Proc. of the Seventh Conference on Natural Language Learning, pp. 142–147. ACL (2003)
Zeldes, A.: The GUM corpus: creating multilayer resources in the classroom. Lang. Resour. Eval. 51(3), 581–612 (2017)
Derczynski, L., Nichols, E., Marieke, E., et al.: Results of the WNUT2017 shared task on novel and emerging entity recognition. In: Proc. of the 3rd Workshop on Noisy User-generated Text, pp. 140–147. ACL (2017)
Stubbs, A., Uzuner, Ö.: Annotating longitudinal clinical narratives for deidentification: the 2014 i2b2/UTHealth corpus. J. Biomed. Inform. 58, S20–S29 (2015)
Acknowledgments
This research was funded by the Key Research and Development Program of China, grant number 2022YFC3005401.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Qi, R., Lou, J., Mao, Y. (2024). Label Prompt Guiding for Two-Stage Few-Shot Named Entity Recognition. In: Huang, DS., Pan, Y., Guo, J. (eds) Advanced Intelligent Computing Technology and Applications. ICIC 2024. Lecture Notes in Computer Science, vol 14873. Springer, Singapore. https://doi.org/10.1007/978-981-97-5615-5_27
Download citation
DOI: https://doi.org/10.1007/978-981-97-5615-5_27
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-5614-8
Online ISBN: 978-981-97-5615-5
eBook Packages: Computer ScienceComputer Science (R0)