Abstract
Few-shot named entity recognition (NER) aims to leverage a small number of labeled examples to extract novel-class named entities from unstructured text. Although existing few-shot NER methods, such as ESD and DecomposedMetaNER, are effective, they are quite complex and not efficient, which makes them unsuitable for real-world applications when the prediction time is a critical factor. In this paper, we propose a simple span-based prototypical framework that follows the metric-based meta-learning paradigm and does not require time-consuming fine-tuning. In addition, the BERT encoding process in our model can be pre-computed and cached, making the final inference process even faster. Experiment results show that, compared with the state-of-the-art models, the proposed framework can achieve comparable effectiveness with much better efficiency.
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
References
Ba, J., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv e-print archive (2016)
Cui, L., Wu, Y., Liu, J., Yang, S., Zhang, Y.: Template-based named entity recognition using BART. In: ACL-IJCNLP (2021)
Das, S.S.S., Katiyar, A., Passonneau, R., Zhang, R.: CONTaiNER: few-shot named entity recognition via contrastive learning. In: ACL (2022)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)
Ding, N., et al.: Few-NERD: a few-shot named entity recognition dataset. In: ACL-IJCNLP (2021)
Friedrich, A., et al.: The SOFC-exp corpus and neural approaches to information extraction in the materials science domain. In: ACL (2020)
Fritzler, A., Logacheva, V., Kretov, M.: Few-shot classification in named entity recognition task. In: SAC (2019)
Fu, J., Huang, X., Liu, P.: SpanNER: named entity re-/recognition as span prediction. In: ACL-IJCNLP (2021)
Gao, T., Han, X., Liu, Z., Sun, M.: Hybrid attention-based prototypical networks for noisy few-shot relation classification. In: AAAI (2019)
Guo, J., et al.: Automated chemical reaction extraction from scientific literature. J. Chem. Inf. Model. 62(9), 2035–2045 (2021)
Hou, Y., et al.: Few-shot slot tagging with collapsed dependency transfer and label-enhanced task-adaptive projection network. In: ACL (2020)
Huang, J., et al.: Few-shot named entity recognition: an empirical baseline study. In: EMNLP (2021)
Kononova, O., et al.: Text-mined dataset of inorganic materials synthesis recipes. Sci. Data 6(1), 1–11 (2019)
Li, Y., Liu, L., Shi, S.: Empirical analysis of unlabeled entity problem in named entity recognition. In: ICLR (2021)
de Lichy, C., Glaude, H., Campbell, W.: Meta-learning for few-shot named entity recognition. In: 1st Workshop on Meta Learning and Its Applications to Natural Language Processing (2021)
Ma, R., Zhou, X., Gui, T., Tan, Y.C., Zhang, Q., Huang, X.: Template-free prompt tuning for few-shot NER. In: NAACL (2022)
Ma, T., Jiang, H., Wu, Q., Zhao, T., Lin, C.Y.: Decomposed meta-learning for few-shot named entity recognition. In: ACL (2022)
Ouchi, H., et al.: Instance-based learning of span representations: a case study through named entity recognition. In: ACL (2020)
Reimers, N., Gurevych, I.: The curse of dense low-dimensional information retrieval for large index sizes. In: ACL (2021)
Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. In: NIPS (2017)
Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H.S., Hospedales, T.M.: Learning to compare: relation network for few-shot learning. In: CVPR (2018)
Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning. In: NISP (2016)
Wang, P., et al.: An enhanced span-based decomposition method for few-shot sequence labeling. In: NAACL (2022)
Wang, X., Han, X., Huang, W., Dong, D., Scott, M.R.: Multi-similarity loss with general pair weighting for deep metric learning. In: CVPR (2019)
Wang, Y., Chu, H., Zhang, C., Gao, J.: Learning from language description: low-shot named entity recognition via decomposed framework. In: EMNLP (2021)
Weston, L., et al.: Named entity recognition and normalization applied to large-scale information extraction from the materials science literature. J. Chem. Inf. Model. 59(9), 3692–3702 (2019)
Yang, Y., Katiyar, A.: Simple and effective few-shot named entity recognition with structured nearest neighbor learning. In: EMNLP (2020)
Yu, J., Bohnet, B., Poesio, M.: Named entity recognition as dependency parsing. In: ACL (2020)
Zhang, Y., Wang, C., Soukaseum, M., Vlachos, D.G., Fang, H.: Unleashing the power of knowledge extraction from scientific literature in catalysis. J. Chem. Inf. Model. 62(14), 3316–3330 (2022)
Acknowledgements
We greatly thanks all reviewers for their constructive comments. The research was supported as part of the Center for Plastics Innovation, an Energy Frontier Research Center, funded by the U.S. Department of Energy (DOE), Office of Science, Basic Energy Sciences (BES), under Award Number DE-SC0021166. The research was also supported in part through the use of DARWIN computing system: DARWIN - A Resource for Computational and Data-intensive Research at the University of Delaware and in the Delaware Region, Rudolf Eigenmann, Benjamin E. Bagozzi, Arthi Jayaraman, William Totten, and Cathy H. Wu, University of Delaware, 2021, URL: https://udspace.udel.edu/handle/19716/29071.
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
Zhang, Y., Fang, H. (2023). Less is More: A Prototypical Framework for Efficient Few-Shot Named Entity Recognition. In: Métais, E., Meziane, F., Sugumaran, V., Manning, W., Reiff-Marganiec, S. (eds) Natural Language Processing and Information Systems. NLDB 2023. Lecture Notes in Computer Science, vol 13913. Springer, Cham. https://doi.org/10.1007/978-3-031-35320-8_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-35320-8_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35319-2
Online ISBN: 978-3-031-35320-8
eBook Packages: Computer ScienceComputer Science (R0)