Abstract
The goal of relation extraction is to obtain relational facts from plain text, which can benefit a variety of natural language processing tasks. To address the challenge of automatically labeling large-scale training data, a distant supervision strategy is introduced to relation extraction by heuristically aligning entity pairs in plain text with the knowledge base. Unfortunately, the method is vulnerable to the noisy label problem due to the incompletion of the exploited knowledge base. Existing works focus on the specific algorithms, but few works summarize the commonalities between different methods and the influencing factors of these denoising mechanisms. In this paper, we propose three main factors that impact the label denoising of distantly supervised relation extraction, including labeling assumption, prior knowledge and confidence level. In order to analyze how these factors influence the denoising effectiveness, we build a unified neural framework with word, sentence and label denoising modules for relation extraction. Then we conduct experiments to evaluate and compare these factors according to ten neural schemes. In addition, we discuss the typical cases of these factors and find that influential word-level prior knowledge and partial confidence for distantly supervised labels can significantly affect the denoising performance. These implicational findings can provide researchers with more insight of distantly supervised relation extraction.
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
Banko, M., Etzioni, O.: The tradeoffs between open and traditional relation extraction. In: Proceedings of ACL 2008, HLT, pp. 28–36 (2008)
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 Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, vol. 1, pp. 541–550. Association for Computational Linguistics (2011)
Huang, X., et al.: Attention-based convolutional neural network for semantic relation extraction. In: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pp. 2526–2536 (2016)
Ji, G., Liu, K., He, S., Zhao, J.: Distant supervision for relation extraction with sentence-level attention and entity descriptions. In: AAAI, pp. 3060–3066 (2017)
Jiang, X., Wang, Q., Li, P., Wang, B.: Relation extraction with multi-instance multi-label convolutional neural networks. In: COLING, pp. 1471–1480 (2016)
Khan, S.H., Hayat, M., Bennamoun, M., Sohel, F.A., Togneri, R.: Cost-sensitive learning of deep feature representations from imbalanced data. IEEE Trans. Neural Netw. Learn. Syst. 29, 3573–3587 (2017)
Kim, J.T., Moldovan, D.I.: Acquisition of semantic patterns for information extraction from corpora. In: Ninth Conference on Artificial Intelligence for Applications, Proceedings, pp. 171–176. IEEE (1993)
Kim, Y.: Convolutional neural networks for sentence classification. In: EMNLP, pp. 1746–1751 (2014)
Kukar, M., Kononenko, I., et al.: Cost-sensitive learning with neural networks. In: ECAI, pp. 445–449 (1998)
Lin, Y., Shen, S., Liu, Z., Luan, H., Sun, M.: Neural relation extraction with selective attention over instances. In: ACL (2016)
Liu, T., Wang, K., Chang, B., Sui, Z.: A soft-label method for noise-tolerant distantly supervised relation extraction. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 1791–1796 (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, vol. 2, pp. 1003–1011. Association for Computational Linguistics (2009)
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
Ritter, A., Zettlemoyer, L., Etzioni, O., et al.: Modeling missing data in distant supervision for information extraction. Trans. Assoc. Comput. Linguist. 1, 367–378 (2013)
Surdeanu, M., Tibshirani, J., Nallapati, R., Manning, C.D.: Multi-instance multi-label learning for relation extraction. In: Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 455–465. Association for Computational Linguistics (2012)
Wu, F., Weld, D.S.: Open information extraction using wikipedia. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pp. 118–127. Association for Computational Linguistics (2010)
Wu, Y., Bamman, D., Russell, S.: Adversarial training for relation extraction. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 1779–1784 (2017)
Xiangrong, Z., Kang, L., Shizhu, H., Jun, Z., et al.: Large scaled relation extraction with reinforcement learning. In: Proceedings of the 15th AAAI Conference on Artificial Intelligence (2018)
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., et al.: Relation classification via convolutional deep neural network. In: COLING, pp. 2335–2344 (2014)
Zhang, T., Huang, M., Zhao, L.: Learning structured representation for text classification via reinforcement learning. In: AAAI (2018)
Zhu, J., Nie, Z., Liu, X., Zhang, B., Wen, J.R.: Statsnowball: a statistical approach to extracting entity relationships. In: Proceedings of the 18th International Conference on World Wide Web, pp. 101–110. ACM (2009)
Acknowledgements
This work is supported by National Natural Science Foundation of China, 61602048, 61520106007, BUPT-SICE Excellent Graduate Students Innovation Funds, 2016.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Sun, T., Zhang, C., Ji, Y. (2018). Factors Impacting the Label Denoising of Neural Relation Extraction. In: Tang, S., Du, DZ., Woodruff, D., Butenko, S. (eds) Algorithmic Aspects in Information and Management. AAIM 2018. Lecture Notes in Computer Science(), vol 11343. Springer, Cham. https://doi.org/10.1007/978-3-030-04618-7_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-04618-7_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-04617-0
Online ISBN: 978-3-030-04618-7
eBook Packages: Computer ScienceComputer Science (R0)