Abstract
An integral task for many natural language processing applications is the extraction of the narrative process described in a document. For understanding such processes we need to recognize the mentioned events and their temporal component. With this information, we can understand the sequence of events i.e. construct a timeline. The main task dealing with the temporal component of events is temporal relation extraction. The goal of temporal relation extraction is to determine how the times of two events are related to one another. For example, such relation would tell us whether one event happened before or after another one. In this paper, we propose a novel architecture for a temporal relation extraction model combining text information with information captured in the form of a temporal event graph. We present our initial results on the domain of clinical documents. Using a temporal event graph with only correct relations, the model achieves F1 score of 83.6% which is higher than any of our state-of-the-art baseline models. This shows the promise of our proposed approach.
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
Bodenreider, O.: The unified medical language system (UMLS): integrating biomedical terminology. Nucleic Acids Res. 32(Database-Issue), 267–270 (2004)
Cheng, F., Miyao, Y.: Classifying temporal relations by bidirectional LSTM over dependency paths. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 1–6 (2017)
Koloski, B., Perdih, T.S., Robnik-Sikonja, M., Pollak, S., Skrlj, B.: Knowledge graph informed fake news classification via heterogeneous representation ensembles. Neurocomputing 496, 208–226 (2022)
Lin, C., Miller, T., Dligach, D., Bethard, S., Savova, G.: A BERT-based universal model for both within-and cross-sentence clinical temporal relation extraction. In: Proceedings of the 2nd Clinical Natural Language Processing Workshop, pp. 65–71 (2019)
Lin, C., Miller, T., Dligach, D., Bethard, S., Savova, G.: EntityBERT: entity-centric masking strategy for model pretraining for the clinical domain. Association for Computational Linguistics (ACL) (2021)
Lin, Y., Lu, K., Yu, S., Cai, T., Zitnik, M.: Multimodal learning on graphs for disease relation extraction. arXiv preprint: arXiv:2203.08893 (2022)
Ning, Q., Subramanian, S., Roth, D.: An improved neural baseline for temporal relation extraction. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 6203–6209 (2019)
Ning, Q., Wu, H., Peng, H., Roth, D.: Improving temporal relation extraction with a globally acquired statistical resource. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 841–851 (2018)
Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543 (2014)
Sun, W., Rumshisky, A., Uzuner, O.: Evaluating temporal relations in clinical text: 2012 i2b2 challenge. J. Am. Med. Inform. Assoc. 20(5), 806–813 (2013)
Tourille, J., Ferret, O., Neveol, A., Tannier, X.: Neural architecture for temporal relation extraction: A Bi-LSTM approach for detecting narrative containers. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 224–230 (2017)
Yasunaga, M., et al.: Deep bidirectional language-knowledge graph pretraining. arXiv preprint: arXiv:2210.09338 (2022)
Zhou, Y., et al.: Clinical temporal relation extraction with probabilistic soft logic regularization and global inference. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI2021) (2021)
Acknowledgements
This work has been financially supported by the Slovenian Research Agency in the young researchers grant.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Knez, T., Žitnik, S. (2023). Temporal Relation Extraction from Clinical Texts Using Knowledge Graphs. In: Nurcan, S., Opdahl, A.L., Mouratidis, H., Tsohou, A. (eds) Research Challenges in Information Science: Information Science and the Connected World. RCIS 2023. Lecture Notes in Business Information Processing, vol 476. Springer, Cham. https://doi.org/10.1007/978-3-031-33080-3_30
Download citation
DOI: https://doi.org/10.1007/978-3-031-33080-3_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33079-7
Online ISBN: 978-3-031-33080-3
eBook Packages: Computer ScienceComputer Science (R0)