ABSTRACT
Medical knowledge bases (KBs), distilled from biomedical literature and regulatory actions, are expected to provide high-quality information to facilitate clinical decision making. Entity disambiguation (also referred to as entity linking) is considered as an essential task in unlocking the wealth of such medical KBs. However, existing medical entity disambiguation methods are not adequate due to word discrepancies between the entities in the KB and the text snippets in the source documents. Recently, graph neural networks (GNNs) have proven to be very effective and provide state-of-the-art results for many real-world applications with graph-structured data. In this paper, we introduce ED-GNN based on three representative GNNs (GraphSAGE, R-GCN, and MAGNN) for medical entity disambiguation. We develop two optimization techniques to fine-tune and improve ED-GNN. First, we introduce a novel strategy to represent entities that are mentioned in text snippets as a query graph. Second, we design an effective negative sampling strategy that identifies hard negative samples to improve the model's disambiguation capability. Compared to the best performing state-of-the-art solutions, our ED-GNN offers an average improvement of 7.3% in terms of F1 score on five real-world datasets.
Supplemental Material
- H. Bunke. What is the distance between graphs. Bulletin of the EATCS, 20:35--39, 1983.Google Scholar
- H. Bunke and K. Shearer. A graph distance metric based on the maximal common subgraph. Pattern Recogn. Lett., 19(3--4):255--259, 1998.Google ScholarDigital Library
- Y. Cao, L. Hou, J. Li, and Z. Liu. Neural collective entity linking. In COLING, pages 675--686, 2018.Google Scholar
- Y. Cen, X. Zou, J. Zhang, H. Yang, J. Zhou, and J. Tang. Representation learning for attributed multiplex heterogeneous network. In SIGKDD, page 1358--1368, 2019.Google ScholarDigital Library
- A. Chisholm and B. Hachey. Entity disambiguation with web links. TACL, 3:145--156, 2015.Google ScholarCross Ref
- P. Christen. Data Matching - Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection. Data-Centric Systems and Applications. Springer, 2012.Google ScholarDigital Library
- J. Dai, M. Zhang, G. Chen, J. Fan, K. Y. Ngiam, and B. C. Ooi. Fine-grained concept linking using neural networks in healthcare. In SIGMOD, pages 51--66, 2018.Google ScholarDigital Library
- S. Das, J. Srinivasan, M. Perry, E. I. Chong, and J. Banerjee. A tale of two graphs: Property graphs as RDF in oracle. In EDBT, pages 762--773, 2014.Google Scholar
- R. I. Dogan, R. Leaman, and Z. Lu. Ncbi disease corpus: A resource for disease name recognition and concept normalization. Journal of Biomedical Informatics, 47:1 -- 10, 2014.Google Scholar
- M. Dredze, P. McNamee, D. Rao, A. Gerber, and T. Finin. Entity disambiguation for knowledge base population. In COLING, page 277--285, 2010.Google Scholar
- X. Fu, J. Zhang, Z. Meng, and I. King. Magnn: Metapath aggregated graph neural network for heterogeneous graph embedding. In WWW, page 2331--2341, 2020.Google ScholarDigital Library
- M. Gardner, J. Grus, et al. AllenNLP: A deep semantic natural language processing platform. CoRR, abs/1803.07640, 2018.Google Scholar
- T. G"a rtner, P. A. Flach, and S. Wrobel. On graph kernels: Hardness results and efficient alternatives. In COLT, volume 2777, pages 129--143, 2003.Google Scholar
- Y. Govind, P. Konda, P. S. G. C., P. Martinkus, P. Nagarajan, H. Li, A. Soundararajan, S. Mudgal, J. R. Ballard, H. Zhang, A. Ardalan, S. Das, D. Paulsen, A. S. Saini, E. Paulson, Y. Park, M. Carter, M. Sun, G. M. Fung, and A. Doan. Entity matching meets data science: A progress report from the magellan project. In SIGMOD, pages 389--403, 2019.Google ScholarDigital Library
- W. L. Hamilton, R. Ying, and J. Leskovec. Inductive representation learning on large graphs. In NIPS, pages 1024--1034, 2017.Google ScholarDigital Library
- W. Hua, K. Zheng, and X. Zhou. Microblog entity linking with social temporal context. In SIGMOD, pages 1761--1775, 2015.Google ScholarDigital Library
- A. E. Johnson, T. J. Pollard, L. Shen, et al. Mimic-iii, a freely accessible critical care database. Scientific data, 3:160035, 2016.Google ScholarCross Ref
- D. P. Kingma and J. Ba. Adam: A method for stochastic optimization. In ICLR, 2015.Google Scholar
- T. N. Kipf and M. Welling. Semi-supervised classification with graph convolutional networks. In ICLR, 2017.Google Scholar
- H. Kö pcke and E. Rahm. Frameworks for entity matching: A comparison. Data Knowl. Eng., 69(2):197--210, 2010.Google ScholarDigital Library
- I. Korkontzelos, D. Piliouras, A. W. Dowsey, and S. Ananiadou. Boosting drug named entity recognition using an aggregate classifier. Artif. Intell. Medicine, 65(2):145--153, 2015.Google ScholarDigital Library
- G. Lample, M. Ballesteros, S. Subramanian, K. Kawakami, and C. Dyer. Neural architectures for named entity recognition. In NAACL, pages 260--270, 2016.Google ScholarCross Ref
- J. Lee, W. Yoon, S. Kim, D. Kim, S. Kim, C. H. So, and J. Kang. Biobert: a pre-trained biomedical language representation model for biomedical text mining. Bioinform., 36(4):1234--1240, 2020.Google ScholarCross Ref
- J. Li, Y. Sun, R. J. Johnson, D. Sciaky, C.-H. Wei, R. Leaman, A. P. Davis, C. J. Mattingly, T. C. Wiegers, and Z. Lu. BioCreative V CDR task corpus: a resource for chemical disease relation extraction. Database, 2016, 05 2016.Google Scholar
- Y. Li, C. Gu, T. Dullien, O. Vinyals, and P. Kohli. Graph matching networks for learning the similarity of graph structured objects. In ICML, pages 3835--3845, 2019.Google Scholar
- Y. Li, D. Tarlow, M. Brockschmidt, and R. S. Zemel. Gated graph sequence neural networks. In ICLR, 2016.Google Scholar
- C. D. Manning, M. Surdeanu, J. Bauer, et al. The Stanford CoreNLP natural language processing toolkit. In ACL, pages 55--60, 2014.Google ScholarCross Ref
- T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean. Distributed representations of words and phrases and their compositionality. In NIPS, pages 3111--3119, 2013.Google ScholarDigital Library
- S. Mudgal, H. Li, T. Rekatsinas, A. Doan, Y. Park, G. Krishnan, R. Deep, E. Arcaute, and V. Raghavendra. Deep learning for entity matching: A design space exploration. In SIGMOD, page 19--34, 2018.Google ScholarDigital Library
- D. Q. Nguyen, T. D. Nguyen, D. Q. Nguyen, and D. Phung. A novel embedding model for knowledge base completion based on convolutional neural network. In NAACL, pages 327--333, 2018.Google ScholarCross Ref
- S. Pradhan, N. Elhadad, W. Chapman, S. Manandhar, and G. Savova. SemEval-2014 task 7: Analysis of clinical text. In Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pages 54--62, 2014.Google ScholarCross Ref
- PyTorch. https://pytorch.org/, 2020.Google Scholar
- R. J. Qureshi, J. Ramel, and H. Cardot. Graph based shapes representation and recognition. In International Workshop on Graph-Based Representations in Pattern Recognition, pages 49--60, 2007.Google ScholarCross Ref
- P. Ristoski, J. Rosati, T. D. Noia, R. D. Leone, and H. Paulheim. Rdf2vec: RDF graph embeddings and their applications. Semantic Web, 10(4):721--752, 2019.Google ScholarCross Ref
- G. K. Savova, J. J. Masanz, P. V. Ogren, J. Zheng, S. Sohn, K. K. Schuler, and C. G. Chute. Mayo clinical text analysis and knowledge extraction system (ctakes): architecture, component evaluation and applications. J. Am. Medical Informatics Assoc., 17(5):507--513, 2010.Google ScholarCross Ref
- M. S. Schlichtkrull, T. N. Kipf, P. Bloem, R. van den Berg, I. Titov, and M. Welling. Modeling relational data with graph convolutional networks. In ESWC, pages 593--607, 2018.Google Scholar
- W. Shen, J. Han, J. Wang, X. Yuan, and Z. Yang. SHINEGoogle Scholar
- : A general framework for domain-specific entity linking with heterogeneous information networks. IEEE Trans. Knowl. Data Eng., 30(2):353--366, 2018.Google ScholarCross Ref
- W. Shen, J. Wang, and J. Han. Entity linking with a knowledge base: Issues, techniques, and solutions. IEEE Trans. Knowl. Data Eng., 27(2):443--460, 2015.Google ScholarCross Ref
- D. Tikk and I. Solt. Improving textual medication extraction using combined conditional random fields and rule-based systems. J. Am. Medical Informatics Assoc., 17(5):540--544, 2010.Google ScholarCross Ref
- E. Tseytlin, K. J. Mitchell, E. Legowski, J. Corrigan, G. Chavan, and R. S. Jacobson. NOBLE - flexible concept recognition for large-scale biomedical natural language processing. BMC Bioinform., 17:32, 2016.Google ScholarCross Ref
- P. Velickovic, G. Cucurull, A. Casanova, A. Romero, P. Liò, and Y. Bengio. Graph attention networks. In ICLR, 2018.Google Scholar
- M. Wang, D. Zheng, Z. Ye, et al. Deep graph library: A graph-centric, highly-performant package for graph neural networks. arXiv:1909.01315, 2019.Google Scholar
- P. Wang, S. Li, and R. Pan. Incorporating GAN for negative sampling in knowledge representation learning. In AAAI, pages 2005--2012, 2018.Google ScholarCross Ref
- Q. Wang, B. Wang, and L. Guo. Knowledge base completion using embeddings and rules. In IJCAI, page 1859--1865, 2015.Google Scholar
- X. Wang, H. Ji, C. Shi, B. Wang, Y. Ye, P. Cui, and P. S. Yu. Heterogeneous graph attention network. In WWW, page 2022--2032, 2019.Google ScholarDigital Library
- D. Wright, Y. Katsis, R. Mehta, and C.-N. Hsu. NormCo: Deep disease normalization for biomedical knowledge base construction. In AKBC 2019, 2019.Google Scholar
- J. Wu, R. Zhang, Y. Mao, H. Guo, M. Soflaei, and J. Huai. Dynamic graph convolutional networks for entity linking. In WWW, pages 1149--1159, 2020.Google ScholarDigital Library
- K. Xu, L. Wu, Z. Wang, Y. Feng, and V. Sheinin. Graph2seq: Graph to sequence learning with attention-based neural networks. CoRR, abs/1804.00823, 2018.Google Scholar
- R. Ying, R. He, K. Chen, P. Eksombatchai, W. L. Hamilton, and J. Leskovec. Graph convolutional neural networks for web-scale recommender systems. In SIGKDD, page 974--983, 2018.Google ScholarDigital Library
- Z. Ying, D. Bourgeois, J. You, M. Zitnik, and J. Leskovec. Gnnexplainer: Generating explanations for graph neural networks. In NeurIPS, pages 9240--9251, 2019.Google Scholar
- C. Zhang, D. Song, C. Huang, A. Swami, and N. V. Chawla. Heterogeneous graph neural network. In SIGKDD, page 793--803, 2019.Google ScholarDigital Library
- Y. Zhang, Q. Yao, Y. Shao, and L. Chen. Nscaching: Simple and efficient negative sampling for knowledge graph embedding. In ICDE, pages 614--625, 2019.Google ScholarCross Ref
- S. Zwicklbauer, C. Seifert, and M. Granitzer. DoSeR - A knowledge-base-agnostic framework for entity disambiguation using semantic embeddings. In ESWC, pages 182--198, 2016.Google ScholarDigital Library
Index Terms
- Medical Entity Disambiguation Using Graph Neural Networks
Recommendations
Combining Textual and Graph-Based Features for Named Entity Disambiguation Using Undirected Probabilistic Graphical Models
Knowledge Engineering and Knowledge ManagementAbstractNamed Entity Disambiguation (NED) is the task of disambiguating named entities in a natural language text by linking them to their corresponding entities in a knowledge base such as DBpedia, which are already recognized. It is an important step in ...
Entity Disambiguation with Linkless Knowledge Bases
WWW '16: Proceedings of the 25th International Conference on World Wide WebNamed Entity Disambiguation is the task of disambiguating named entity mentions in natural language text and link them to their corresponding entries in a reference knowledge base (e.g. Wikipedia). Such disambiguation can help add semantics to plain ...
An optimization framework for entity recognition and disambiguation
ERD '14: Proceedings of the first international workshop on Entity recognition & disambiguationWe present a system for entity recognition and disambiguation (ERD) in short text, aiming at identifying all text fragments referring to an entity contained in Freebase. The task is organized in two steps. Given a short text the first step is ...
Comments