Advertisement

A New Method for Complex Triplet Extraction of Biomedical Texts

  • Xiao Wang
  • Qing Li
  • Xuehai DingEmail author
  • Guoqing Zhang
  • Linhong Weng
  • Minjie Ding
Conference paper
  • 514 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11776)

Abstract

Extracting biomedical triplet is one of the most important tasks in medical knowledge graph construction. Relations in complex biomedical text are overlap heavily. Although existing biomedical relation extraction methods have higher accuracy, they still have two problems. First, most of those methods hardly consider relations overlap problem. A lot of precious biomedical information is neglected. In addition, the entities in biomedical text are intensive, and the contextual information association also affects the understanding of the meaning of biomedical texts. Methods often used to encode sentence, like canonical bidirectional recurrent neural networks (BiRNN) or convolutional neural networks (CNN), are difficult to capture enough information from biomedical text. In this paper, we propose a new end-to-end triplet extraction method to address the complex triplet extraction problem in biomedical text. In our model, sentences are encoded by Recurrent Convolutional Neural Network (RCNN), which combines the advantages of BiRNN and CNN flexibly, containing more information of sentence. Experimental results on biomedical dataset and general field dataset show that our method is effective.

Keywords

Triplet extraction Biomedical text Neural network Relation overlap Semantic vector 

Notes

Acknowledgments

This work was supported by the National key research and development program of China (No. 2017YFE0117500), National Key R&D Program of China, Grant (NO. 2016YFC0901904, 2016YFC0901604) and Science and Technology Committee of Shanghai Municipality (No. 16010500400).

References

  1. 1.
    Luo, Y., et al.: Segment convolutional neural networks (Seg-CNNs) for classifying relations in clinical notes. J. Am. Med. Inform. Assoc. 25(1), 93–98 (2018)CrossRefGoogle Scholar
  2. 2.
    Luo, Y.: Recurrent neural networks for classifying relations in clinical notes. J. Biomed. Inform. 72, 85–95 (2017)CrossRefGoogle Scholar
  3. 3.
    He, B., Guan, Y., Dai, R.: Classifying medical relations in clinical text via convolutional neural networks. Artif. Intell. Med. 93, 43–49 (2019)CrossRefGoogle Scholar
  4. 4.
    Uzuner, Ö., South, B.R., Shen, S., et al.: 2010 i2b2/VA challenge on concepts, assertions, and relations in clinical text. J. Am. Med. Inform. Assoc. 18(5), 552–556 (2011)CrossRefGoogle Scholar
  5. 5.
    Li, F., Zhang, M., Fu, G., et al.: A neural joint model for entity and relation extraction from biomedical text. BMC Bioinform. 18(1), 198 (2017)CrossRefGoogle Scholar
  6. 6.
    Zeng, X., et al.: Extracting relational facts by an end-to-end neural model with copy mechanism. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Long Papers, vol. 1 (2018)Google Scholar
  7. 7.
    Lai, S., Xu, L., Liu, K., Zhao, J.: Recurrent convolutional neural networks for text classification. In: Twenty-Ninth AAAI Conference on Artificial Intelligence (2015)Google Scholar
  8. 8.
    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)Google Scholar
  9. 9.
    Xu, K., Zhou, Z., Hao, T., Liu, W.: A bidirectional LSTM and conditional random fields approach to medical named entity recognition. In: Hassanien, A.E., Shaalan, K., Gaber, T., Tolba, Mohamed F. (eds.) AISI 2017. AISC, vol. 639, pp. 355–365. Springer, Cham (2018).  https://doi.org/10.1007/978-3-319-64861-3_33CrossRefGoogle Scholar
  10. 10.
    Zhu, Ji., et al.: Relation classification via target-concentrated attention CNNs (2017)CrossRefGoogle Scholar
  11. 11.
    Miwa, M., Bansal, M.: End-to-end relation extraction using LSTMs on sequences and tree structures. In: Proceedings of ACL, pp. 1105–1116 (2016)Google Scholar
  12. 12.
    Zheng, S., et al.: Joint entity and relation extraction based on a hybrid neural network. Neurocomputing 257, 59–66 (2017)CrossRefGoogle Scholar
  13. 13.
    Gupta, P., Schtze, H., Andrassy, B.: Table filling multi-task recurrent neural network for joint entity and relation extraction. In: Proceedings of COLING, pp. 2537–2547 (2016)Google Scholar
  14. 14.
    Li, Q., Ji, H.: Incremental joint extraction of entity mentions and relations. In: Proceedings of ACL, pp. 402–412 (2014)Google Scholar
  15. 15.
    Miwa, M., Sasaki, Y.: Modeling joint entity and relation extraction with table representation. In: Proceedings of EMNLP, pp. 1858–1869 (2014)Google Scholar
  16. 16.
    Yu, X., Lam, W.: Jointly identifying entities and extracting relations in encyclopedia text via a graphical model approach. In: Proceedings of COLING, pp. 1399–1407 (2010)Google Scholar
  17. 17.
    Zheng, S., et al.: Joint extraction of entities and relations based on a novel tagging scheme (2017)Google Scholar
  18. 18.
    Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling (2014). arXiv preprint: arXiv:1412.3555
  19. 19.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  20. 20.
    Klambauer, G., Unterthiner, T., Mayr, A., Hochreiter, S.: Self-normalizing neural networks. In: Advances in NIPS, pp. 971–980 (2017)Google Scholar
  21. 21.
    Sahu, S.K., Anand, A., Oruganty, K., Gattu, M.: Relation extraction from clinical texts using domain invariant convolutional neural network (2016). arXiv preprint: arXiv:1606.09370
  22. 22.
  23. 23.
    Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: Proceedings of ICLR, pp. 1–15 (2015)Google Scholar
  24. 24.

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.School of Computer Engineering and ScienceShanghai UniversityShanghaiChina
  2. 2.Bio-Med Big Data Center, CAS-Key Laboratory of Computational Biology, CAS-MPG Partner Institute for Computational Biology, Shanghai Institute of Nutrition and Health, Shanghai Institutes for Biological SciencesUniversity of Chinese Academy of Sciences, Chinese Academy of SciencesShanghaiChina

Personalised recommendations