Abstract
Clustering-based relation discovery is one of the important methods in the field of open relation extraction (OpenRE). However, samples residing in semantically overlapping regions often remain indistinguishable. In this work, we propose an adaptive clustering method based on a relation repository to explicitly model the semantic differences between clusters to mitigate the relational semantic overlap in unlabeled data. Specifically, we construct difficult samples and use bidirectional margin loss to constrain the differences of each sample and apply self-supervised contrastive learning to labeled data. Combined with contrastive learning of unlabeled data, we construct a relation repository to explicitly model the semantic differences between clusters. Meanwhile, we place greater emphasis on the difficult samples located on the boundary, enabling the model to adaptively adjust the decision boundary, which lead to generate cluster-friendly relation representations to improve the effect of open relation extraction. Experiments on two public datasets show that our method can effectively improve the performance of open relation extraction.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bagga, A., Baldwin, B.: Entity-based cross-document coreferencing using the vector space model. In: Proceeding of ACL, pp. 79ā85 (1998)
Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL, pp. 4171ā4186 (2019)
ElSahar, H., Demidova, E., Gottschalk, S., Gravier, C., Laforest, F.: Unsupervised open relation extraction. CoRR abs/1801.07174 (2018)
Gutmann, M., HyvƤrinen, A.: Noise-contrastive estimation: a new estimation principle for unnormalized statistical models. J. Mach. Learn. Res. 9, 297ā304 (2010)
Han, X., et al.: Fewrel: a large-scale supervised few-shot relation classification dataset with state-of-the-art evaluation. In: Proceedings of EMNLP, pp. 4803ā4809 (2018)
Hu, X., Wen, L., Xu, Y., Zhang, C., Yu, P.S.: Selfore: self-supervised relational feature learning for open relation extraction. In: Proceedings of EMNLP, pp. 3673ā3682 (2020)
Hubert, L.J., Arabie, P.: Comparing partitions. J. Classif. 2, 193ā218 (1985)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7ā9 May 2015, Conference Track Proceedings (2015)
Laurens, V.D.M., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(2605), 2579ā2605 (2008)
Marcheggiani, D., Titov, I.: Discrete-state variational autoencoders for joint discovery and factorization of relations. Trans. Assoc. Comput. Linguist. 4(2), 231ā244 (2016)
Rosenberg, A., Hirschberg, J.: V-measure: a conditional entropy-based external cluster evaluation measure. In: Proceedings of EMNLP, pp. 410ā420 (2007)
Tran, T.T., Le, P., Ananiadou, S.: Revisiting unsupervised relation extraction. In: Proceedings of ACL, pp. 7498ā7505 (2020)
Wu, R., et al.: Open relation extraction: Relational knowledge transfer from supervised data to unsupervised data. In: Proceedings of EMNLP, pp. 219ā228 (2019)
Zhan, X., Xie, J., Liu, Z., Ong, Y., Loy, C.C.: Online deep clustering for unsupervised representation learning. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6687ā6696 (2020)
Zhang, Y., Zhong, V., Chen, D., Angeli, G., Manning, C.D.: Position-aware attention and supervised data improve slot filling. In: Proceedings of EMNLP, pp. 35ā45 (2017)
Zhao, J., Gui, T., Zhang, Q., Zhou, Y.: A relation-oriented clustering method for open relation extraction. In: Proceedings of EMNLP, pp. 9707ā9718 (2021)
Acknowledgements
We thank the anonymous reviewers. This work is supported by the Open Project Program of the National Defense Key Laboratory of Electronic Information Equipment System Research under Grant DXZT-JCZZ-2017-009.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chang, K., Jian, P. (2023). Relation Repository Based Adaptive Clustering forĀ Open Relation Extraction. In: Wang, H., Han, X., Liu, M., Cheng, G., Liu, Y., Zhang, N. (eds) Knowledge Graph and Semantic Computing: Knowledge Graph Empowers Artificial General Intelligence. CCKS 2023. Communications in Computer and Information Science, vol 1923. Springer, Singapore. https://doi.org/10.1007/978-981-99-7224-1_8
Download citation
DOI: https://doi.org/10.1007/978-981-99-7224-1_8
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-7223-4
Online ISBN: 978-981-99-7224-1
eBook Packages: Computer ScienceComputer Science (R0)