Abstract
Medical relation extraction discovers relations between entity mentions in unstructured text, such as biomedical literature. Dependency structures have proven to be useful for this task. However, how to effectively make use of structural information from dependency forests remains a challenging research question. Existing approaches directly employing weighted graphs or variable graphs, where the graph can be viewed as a dependency forest, may not always yield optimal results. In this work, we propose a novel model, the auto-learning convolution-based graph convolutional network (AC-GCN), which learns weighted graphs using a 2D convolutional network. The convolution operation is performed over dependency forests to obtain highly informative features useful for medical relation extraction. Results obtained on three biomedical benchmarks show that our model is able to better learn the structural information of the dependency forests, providing significantly better results than those of previous approaches.
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
Quirk C, Poon H.: Distant supervision for relation extraction beyond the sentence boundary. In: EACL, pp. 1171–1182 (2017)
Peng, N., Poon, H., Quirk, C., Toutanova, K., Yih, W.T.: Cross sentence N-ary relation extraction with graph LSTMs. Trans. Assoc. Comput. Linguist. 5, 101–115 (2017)
Zhang, Y., Qi, P., Manning, C. D.: Graph convolution over pruned dependency trees improves relation extraction. In: EMNLP, pp. 2205–2215 (2018)
Xu, Y., Mou, L., Li, G., Chen, Y., Peng, H., Jin, Z.: Classifying relations via long short term memory networks along shortest dependency paths. In: EMNLP, pp. 1785–1794 (2015)
Song, L., Zhang, Y., Wang, Z., Gildea, D.: N-ary relation extraction using graph-state LSTM. In: EMNLP, pp. 2226–2235 (2018)
Lease, M., Charniak, E.: Parsing biomedical literature. In: Dale, R., Wong, K.-F., Su, J., Kwong, O.Y. (eds.) IJCNLP 2005. LNCS (LNAI), vol. 3651, pp. 58–69. Springer, Heidelberg (2005). https://doi.org/10.1007/11562214_6
Jin, L., Song, L., Zhang, Y., Xu, K., Ma, W.Y., Yu, D.: Relation extraction exploiting full dependency forests. In: AAAI, vol. 34, no. 05, pp. 8034–8041 (2020)
Guo, Z., Nan, G., Lu, W., Cohen, S.B.: Learning latent forests for medical relation extraction. In: IJCAI, pp. 3651–3657 (2020)
Kim, Y., Denton, C., Hoang, L., Rush, A.M.: Structured attention networks. In: ICLR (2017)
LeCun, Y., Bengio, Y.: Convolutional networks for images, speech, and time series. In: The Handbook of Brain Theory and Neural Networks, vol. 3361, no. 10, p. 1995 (1995)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)
Krallinger, M., et al.: Overview of the biocreative VI chemical-protein interaction track. In: Proceedings of the Sixth BioCreative Challenge Evaluation Workshop, vol. 1, pp. 141–146 (2017)
Sousa, D., Lamurias, A., Couto, F.M.: A silver standard corpus of human phenotype-gene relations. In: NAACL-HLT, pp. 1487–1492 (2019)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)
Xu, K., Li, C., Tian, Y., Sonobe, T., Kawarabayashi, K.I., Jegelka, S.: Representation learning on graphs with jumping knowledge networks. In: ICML, pp. 5453–5462 (2018)
Miwa, M., Bansal, M.: End-to-end relation extraction using LSTMs on sequences and tree structures. In: ACL, pp. 1105–1116 (2016)
Liu, S., et al.: Extracting chemical-protein relations using attention-based neural networks. Database J. Biol. Databases Curation 2018, bay102 (2018)
Verga, P., Strubell, E., McCallum, A.: Simultaneously self-attending to all mentions for full-abstract biological relation extraction. In: NAACL-HLT, pp. 872–884 (2018)
Lee, J., et al.: BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 36(4), 1234–1240 (2020)
Guo, Z., Zhang, Y., Lu, W.: Attention guided graph convolutional networks for relation extraction. In: ACL, pp. 241–251 (2019)
Song, L., Zhang, Y., Gildea, D., Yu, M., Wang, Z., Su, J.: Leveraging dependency forest for neural medical relation extraction. In: EMNLP-IJCNLP, pp. 208–218 (2019)
Acknowledgement
This work was financially supported by the National Natural Science Foundation of China (No. 62072070).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Qian, M. et al. (2021). Auto-learning Convolution-Based Graph Convolutional Network for Medical Relation Extraction. In: Lin, H., Zhang, M., Pang, L. (eds) Information Retrieval. CCIR 2021. Lecture Notes in Computer Science(), vol 13026. Springer, Cham. https://doi.org/10.1007/978-3-030-88189-4_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-88189-4_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-88188-7
Online ISBN: 978-3-030-88189-4
eBook Packages: Computer ScienceComputer Science (R0)