Abstract
Distant supervision relation extraction is a promising approach to find new relation instances from large text corpora. Most previous works employ the top 1 strategy, i.e., predicting the relation of a sentence with the highest confidence score, which is not always the optimal solution. To improve distant supervision relation extraction, this work applies the best from top k strategy to explore the possibility of relations with lower confidence scores. We approach the best from top k strategy using a deep reinforcement learning framework, where the model learns to select the optimal relation among the top k candidates for better predictions. Specifically, we employ a deep Q-network, trained to optimize a reward function that reflects the extraction performance under distant supervision. The experiments on three public datasets - of news articles, Wikipedia and biomedical papers - demonstrate that the proposed strategy improves the performance of traditional state-of-the-art relation extractors significantly. We achieve an improvement of 5.13% in average F\(_1\)-score over four competitive baselines.
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
Notes
- 1.
TF-IDF counts are computed based on the training sentences.
- 2.
We choose k by ranging it from 1 to 5 in our experiments, the model achieves the best performance in most cases when k = 3.
- 3.
- 4.
- 5.
- 6.
References
Feng, J., Huang, M., Zhao, L., Yang, Y., Zhu, X.: Reinforcement learning for relation classification from noisy data. In: Proceedings of AAAI 2018 (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 ACL 2011, pp. 541–550 (2011)
Koch, M., Gilmer, J., Soderland, S., Weld, D.S.: Type-aware distantly supervised relation extraction with linked arguments. In: Proceedings of EMNLP 2014, pp. 1891–1901 (2014)
Lin, Y., Shen, S., Liu, Z., Luan, H., Sun, M.: Neural relation extraction with selective attention over instances. In: Proceedings of ACL 2016, pp. 2124–2133 (2016)
Ling, X., Weld, D.S.: Fine-grained entity recognition. In: Proceedings AAAI 2012, vol. 12, pp. 94–100 (2012)
Lockard, C., Dong, X.L., Einolghozati, A., Shiralkar, P.: CERES: distantly supervised relation extraction from the semi-structured web. In: Proceedings of VLDB 2018, pp. 1084–1096 (2018)
Lourentzou, I., Alba, A., Coden, A., Gentile, A.L., Gruhl, D., Welch, S.: Mining relations from unstructured content. In: Phung, D., Tseng, V.S., Webb, G.I., Ho, B., Ganji, M., Rashidi, L. (eds.) PAKDD 2018. LNCS, vol. 10938, pp. 363–375. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-93037-4_29
Mintz, M., Bills, S., Snow, R., Jurafsky, D.: Distant supervision for relation extraction without labeled data. In: Proceedings of ACL 2009, pp. 1003–1011 (2009)
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)
Narasimhan, K., Yala, A., Barzilay, R.: Improving information extraction by acquiring external evidence with reinforcement learning. In: Proceedings of EMNLP 2016, pp. 2355–2365 (2016)
Pyysalo, S., et al.: BioInfer: a corpus for information extraction in the biomedical domain. BMC Bioinform. 8(1), 50 (2007)
Qin, P., Xu, W., Wang, W.Y.: Robust distant supervision relation extraction via deep reinforcement learning. In: Proceedings of ACL 2018, pp. 2137–2147 (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, 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 EMNLP 2012, pp. 455–465 (2012)
Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning. MIT Press, Cambridge (1998)
Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3–4), 279–292 (1992)
Zeng, D., Liu, K., Chen, Y., Zhao, J.: Distant supervision for relation extraction via piecewise convolutional neural networks. In: Proceedings of EMNLP 2015, pp. 1753–1762 (2015)
Zeng, X., He, S., Liu, K., Zhao, J.: Large scaled relation extraction with reinforcement learning. In: Proceedings of AAAI 2018 (2018)
Zhou, G., Su, J., Jie, Z., Zhang, M.: Exploring various knowledge in relation extraction. In: Proceedings of ACL 2005, pp. 427–434 (2005)
Acknowledgements
This work is partially funded by the National Science Foundation of China under Grant 61170165, Grant 61702279, Grant 61602260, and Grant 61502095.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Gui, Y., Liu, Q., Lu, T., Gao, Z. (2019). Best from Top k Versus Top 1: Improving Distant Supervision Relation Extraction with Deep Reinforcement Learning. In: Yang, Q., Zhou, ZH., Gong, Z., Zhang, ML., Huang, SJ. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2019. Lecture Notes in Computer Science(), vol 11441. Springer, Cham. https://doi.org/10.1007/978-3-030-16142-2_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-16142-2_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-16141-5
Online ISBN: 978-3-030-16142-2
eBook Packages: Computer ScienceComputer Science (R0)