Abstract
It was found that relation extraction (RE) suffered from the lack of data. A widely used solution is to use distant supervision, but it brings many wrong labeled sentences. Previous work performed bag-level training to reduce the effect of noisy data. However, these methods are suboptimal because they cannot handle the situation where all the sentences in a bag are wrong labeled. The best way to reduce noise is to recognize the wrong labels and correct them. In this paper, we propose a novel model focusing on dynamically correcting wrong labels, which can train models at sentence level and improve the quality of the dataset without reducing its quantity. A semantic similarity module and a new label correction algorithm are designed. We combined semantic similarity and classification probability to evaluate the original label, and correct it if it is wrong. The proposed method works as an additional module that can be applied to any classification models. Experiments show that the proposed method can accurately correct wrong labels, both false positive and false negative, and greatly improve the performance of relation classification comparing to state-of-the-art systems.
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
Bunescu, R.C., Mooney, R.J.: A shortest path dependency kernel for relation extraction. In: Proceedings of HLT/EMNLP, pp. 724–731. Association for Computational Linguistics (2005)
Feng, J., Huang, M., Zhao, L., Yang, Y., Zhu, X.: Reinforcement learning for relation classification from noisy data. In: Proceedings of AAAI (2018)
Hoffmann, R., Zhang, C., Ling, X., Zettlemoyer, L., Weld, D.S.: Knowledge-based weak supervision for information extraction of overlapping relations. In: Proceedings of the 49th ACL: Human Language Technologies, vol. 1, pp. 541–550 (2011)
Kambhatla, N.: Combining lexical, syntactic, and semantic features with maximum entropy models for extracting relations. In: Proceedings of the ACL 2004 on Interactive Poster and Demonstration Sessions, p. 22 (2004)
Lei, K., et al.: Cooperative denoising for distantly supervised relation extraction. In: Proceedings of the 27th International Conference on Computational Linguistics, pp. 426–436 (2018)
Lin, Y., Shen, S., Liu, Z., Luan, H., Sun, M.: Neural relation extraction with selective attention over instances. In: Proceedings of the 54th ACL (Volume 1: Long Papers), vol. 1, pp. 2124–2133 (2016)
Liu, L., et al.: Heterogeneous supervision for relation extraction: A representation learning approach. arXiv preprint arXiv:1707.00166 (2017)
Liu, T., Wang, K., Chang, B., Sui, Z.: A soft-label method for noise-tolerant distantly supervised relation extraction. In: EMNLP, pp. 1790–1795 (2017)
Mintz, M., Bills, S., Snow, R., Jurafsky, D.: Distant supervision for relation extraction without labeled data. In: Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2-Volume 2, pp. 1003–1011. Association for Computational Linguistics (2009)
Nguyen, T.H., Grishman, R.: Relation extraction: perspective from convolutional neural networks. In: Proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing, pp. 39–48 (2015)
Pearson, K.: Note on regression and inheritance in the case of two parents. Proc. Roy. Soc. Lond. 58, 240–242 (1895)
Qian, L., Zhou, G., Kong, F., Zhu, Q., Qian, P.: Exploiting constituent dependencies for tree kernel-based semantic relation extraction. In: Proceedings of the 22nd International Conference on Computational Linguistics, vol. 1, pp. 697–704. Association for Computational Linguistics (2008)
Qin, P., Xu, W., Wang, W.Y.: Dsgan: Generative adversarial training for distant supervision relation extraction. arXiv preprint arXiv:1805.09929 (2018)
Qin, P., Xu, W., Wang, W.Y.: Robust distant supervision relation extraction via deep reinforcement learning. arXiv preprint arXiv:1805.09927 (2018)
Riedel, S., Yao, L., McCallum, A.: Modeling relations and their mentions without labeled text. In: Balcázar, J.L., Bonchi, F., Gionis, A., Sebag, M. (eds.) ECML PKDD 2010. LNCS (LNAI), vol. 6323, pp. 148–163. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15939-8_10
Santos, C.N.d., Xiang, B., Zhou, B.: Classifying relations by ranking with convolutional neural networks. arXiv preprint arXiv:1504.06580 (2015)
Suchanek, F.M., Ifrim, G., Weikum, G.: Combining linguistic and statistical analysis to extract relations from web documents. In: the 12th ACM SIGKDD, pp. 712–717. ACM (2006)
Wang, L., Cao, Z., De Melo, G., Liu, Z.: Relation classification via multi-level attention CNNs. In: the 54th ACL (long papers), vol. 1, pp. 1298–1307 (2016)
Zeng, D., Liu, K., Chen, Y., Zhao, J.: Distant supervision for relation extraction via piecewise convolutional neural networks. In: EMNLP. pp. 1753–1762 (2015)
Zeng, D., Liu, K., Lai, S., Zhou, G., Zhao, J.: Relation classification via convolutional deep neural network. In: COLING: Technical Papers, pp. 2335–2344 (2014)
Zhang, D., Wang, D.: Relation classification via recurrent neural network. arXiv preprint arXiv:1508.01006 (2015)
Zhou, P., et al.: Attention-based bidirectional long short-term memory networks for relation classification. In: Proceedings of the 54th ACL (Volume 2: Short Papers), vol. 2, pp. 207–212 (2016)
Acknowledgements
This research work has been funded by the National Natural Science Foundation of China (Grant No. 61772337, U1736207), and the National Key Research and Development Program of China NO. 2016QY03D0604.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhu, X., Liu, G., Su, B., Nees, J.P. (2019). Dynamic Label Correction for Distant Supervision Relation Extraction via Semantic Similarity. In: Tang, J., Kan, MY., Zhao, D., Li, S., Zan, H. (eds) Natural Language Processing and Chinese Computing. NLPCC 2019. Lecture Notes in Computer Science(), vol 11839. Springer, Cham. https://doi.org/10.1007/978-3-030-32236-6_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-32236-6_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32235-9
Online ISBN: 978-3-030-32236-6
eBook Packages: Computer ScienceComputer Science (R0)
