Abstract
Few-shot relation classification (RC) aims to determine the labeled relation between two entities in a given sentence using only a few training instances. Previous studies integrate models with explicit triple knowledge, using the inherent concepts of entities to improve the instance representation. However, these studies neglect the implicit structural knowledge present in the knowledge graph (KG). In this paper, we present SKProto, a knowledge-enhanced prototypical network that leverages deep structured semantic knowledge from the multi-hop neighbors of entity-linked concepts. Specifically, we propose a concept-guided hybrid attention mechanism to learn implicit structural semantic knowledge for enhancing the context-aware instance representation. To further distinguish subtle semantic differences among the concepts, the multi-granularity semantic distinction approach is proposed to construct the negative samples with various difficulties (i.e. hard, medium, and easy) based on the conceptual hierarchical structure. Experimental results on the FewRel 2.0 benchmark show that SKProto outperforms state-of-the-art models. We also demonstrate that SKProto has better robustness than other competitive models in low-shot scenarios.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Following KEFDA, we adopt a conceptual graph containing a general domain part and a specific domain part.
- 2.
- 3.
- 4.
- 5.
- 6.
References
Bansal, T., Gunasekaran, K., Wang, T., Munkhdalai, T., McCallum, A.: Diverse distributions of self-supervised tasks for meta-learning in NLP. In: EMNLP, pp. 5812–5824 (2021)
Gao, T., et al.: FewRel 2.0: towards more challenging few-shot relation classification. In: EMNLP-IJCNLP, pp. 6250–6255 (2019)
Hao, J., Chen, M., Yu, W., Sun, Y., Wang, W.: Universal representation learning of knowledge bases by jointly embedding instances and ontological concepts. In: SIGKDD, pp. 1709–1719 (2019)
Lin, Z., et al.: A structured self-attentive sentence embedding. arXiv preprint arXiv:1703.03130 (2017)
Mahony, N.O., Campbell, S., Krpalkova, L., Carvalho, A., Walsh, J., Riordan, D.: Representation learning for fine-grained change detection. Sensors 21, 4486 (2021)
Zhang, N., et al.: Long-tail relation extraction via knowledge graph embeddings and graph convolution networks. In: NAACL (2019)
Wu, R., et al.: Open relation extraction: relational knowledge transfer from supervised data to unsupervised data. In: EMNLP (2019)
Wang, H., Qin, K., Zakari, R.Y., Lu, G., Yin, J.: Deep neural network-based relation extraction: an overview. Neural. Comput. Appl. 34, 1–21 (2022)
Yang, B., Yih, W.T., He, X., Gao, J., Deng, L.: Embedding entities and relations for learning and inference in knowledge bases. In: ICLR (2015)
Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. In: arXiv preprint arXiv:1607.06450 (2016)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML (2017)
Gao, T., Han, X., Liu, Z., Sun, M.: Hybrid attention-based prototypical networks for noisy few-shot relation classification. In: AAAI, vol. 33, pp. 6407–6414 (2019)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: STAT (2015)
Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: CVPR, vol. 2, pp. 1735–1742 (2006)
Han, X.: Fewrel: a large-scale supervised few-shot relation classification dataset with state-of-the-art evaluation. In: EMNLP, pp. 4803–4809 (2018)
Hendrycks, D., Gimpel, K.: Gaussian error linear units (GELUs). arXiv preprint arXiv:1606.08415 (2016)
Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT, pp. 4171–4186 (2019)
Miwa, M., Bansal, M.: End-to-end relation extraction using LSTMs on sequences and tree structures. In: ACL, pp. 1105–1116 (2016)
Nichol, A., Achiam, J., Schulman, J.: On first-order meta-learning algorithms. arXiv: Learning (2018)
Obamuyide, A., Vlachos, A.: Meta-learning improves lifelong relation extraction. In: ACL (2019)
Obamuyide, A., Vlachos, A.: Model-agnostic meta-learning for relation classification with limited supervision. In: ACL (2019)
Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)
Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. In: NeurIPS (2017)
Soares, L., FitzGerald, N., Ling, J., Kwiatkowski, T.: Matching the blanks: distributional similarity for relation learning. In: ACL (2019)
Wan, C., Zhang, T., Xiong, Z., Ye, H.: Representation learning for fault diagnosis with contrastive predictive coding. In: SAFEPROCESS, pp. 1–5 (2021)
Wang, Q., Van Hoof, H.: Model-based meta reinforcement learning using graph structured surrogate models and amortized policy search. In: ICML (2022)
Xiong, W., Yu, M., Chang, S., Guo, X., Wang, W.Y.: One-shot relational learning for knowledge graphs. In: EMNLP, pp. 1980–1990 (2018)
Yang, S., Zhang, Y., Niu, G., Zhao, Q., Pu, S.: Entity concept-enhanced few-shot relation extraction. In: ACL-IJCNLP, pp. 987–991 (2021)
Zhang, J., Zhu, J., Yang, Y., Shi, W., Zhang, C., Wang, H.: Knowledge-enhanced domain adaptation in few-shot relation classification. In: SIGKDD (2021)
Zhang, Y., Qi, P., Manning, C.D.: Graph convolution over pruned dependency trees improves relation extraction. In: EMNLP, pp. 2205–2215 (2018)
Zhenzhen, L., Zhang, Y., Nie, J.Y., Li, D.: Improving few-shot relation classification by prototypical representation learning with definition text. In: NAACL (2022)
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
Li, Y., Zhang, T., Li, D., He, X. (2023). Knowledge-Enhanced Prototypical Network with Structural Semantics for Few-Shot Relation Classification. In: Kashima, H., Ide, T., Peng, WC. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2023. Lecture Notes in Computer Science(), vol 13937. Springer, Cham. https://doi.org/10.1007/978-3-031-33380-4_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-33380-4_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33379-8
Online ISBN: 978-3-031-33380-4
eBook Packages: Computer ScienceComputer Science (R0)