Existing pharmaceutical information extraction research often focus on standalone entity or relationship identification tasks over drug instructions. There is a lack of a holistic solution for drug knowledge extraction. Moreover, current methods perform poorly in extracting fine-grained interaction relations from drug instructions. To solve these problems, this paper proposes an information extraction framework for drug instructions. The framework proposes deep learning models with fine-tuned pre-training models for entity recognition and relation extraction. In addition, it incorporates an novel entity pair calibration process to promote the performance for fine-grained relation extraction. The framework experiments on more than 60k Chinese drug description sentences from 4000 drug instructions. Empirical results show that the framework can successfully identify drug related entities (F1 3 0.95) and their relations (F1 3 0.83) from the realistic dataset, and the entity pair calibration plays an important role (~5% F1 score improvement) in extracting fine-grained relations.<\/p>","DOI":"10.4018\/ijswis.307908","type":"journal-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T17:06:57Z","timestamp":1660324017000},"page":"1-23","source":"Crossref","is-referenced-by-count":3,"title":["Fine-Grained Drug Interaction Extraction Based on Entity Pair Calibration and Pre-Training Model for Chinese Drug Instructions"],"prefix":"10.4018","volume":"18","author":[{"given":"Xiaoliang","family":"Zhang","sequence":"first","affiliation":[{"name":"The First Affiliated Hospital of Nanjing Medical University, China"}]},{"given":"Feng","family":"Gao","sequence":"additional","affiliation":[{"name":"Wuhan University of Science and Technology, China"}]},{"given":"Lunsheng","family":"Zhou","sequence":"additional","affiliation":[{"name":"Wuhan University of Science and Technology, China"}]},{"given":"Shenqi","family":"Jing","sequence":"additional","affiliation":[{"name":"Nanjing Medical University, China"}]},{"given":"Zhongmin","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing Medical University, China"}]},{"given":"Yongqing","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing Medical University, China"}]},{"given":"Shumei","family":"Miao","sequence":"additional","affiliation":[{"name":"Nanjing Medical University, China"}]},{"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing Medical University, China"}]},{"given":"Jianjun","family":"Guo","sequence":"additional","affiliation":[{"name":"Nanjing Medical University, China"}]},{"given":"Tao","family":"Shan","sequence":"additional","affiliation":[{"name":"Nanjing Medical University, China"}]},{"given":"Yun","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanjing Medical University, China"}]}],"member":"2432","reference":[{"key":"IJSWIS.307908-0","doi-asserted-by":"publisher","DOI":"10.4018\/JOEUC.294580"},{"key":"IJSWIS.307908-1","unstructured":"Bao, Y., Wu, M., Chang, S., & Barzilay, R. (2019). Few-shot text classification with distributional signatures. arXiv preprint arXiv:1908.06039."},{"issue":"DEC","key":"IJSWIS.307908-2","first-page":"34","article-title":"Joint entity recognition and relation extraction as a multi-head selection problem.","volume":"114","author":"B.Giannis","year":"2018","journal-title":"Expert Systems with Applications"},{"key":"IJSWIS.307908-3","doi-asserted-by":"publisher","DOI":"10.4018\/IJSWIS.2016070101"},{"key":"IJSWIS.307908-4","doi-asserted-by":"publisher","DOI":"10.3390\/app11188319"},{"key":"IJSWIS.307908-5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3124365"},{"key":"IJSWIS.307908-6","unstructured":"Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805."},{"key":"IJSWIS.307908-7","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36077-8_16"},{"key":"IJSWIS.307908-8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2021.103707"},{"issue":"3","key":"IJSWIS.307908-9","first-page":"169","article-title":"Research progress of entity relation extraction base on deep learning framework.","volume":"36","author":"L. I.Feng-Lin","year":"2018","journal-title":"Information Science"},{"key":"IJSWIS.307908-10","doi-asserted-by":"publisher","DOI":"10.1145\/3500931.3500939"},{"key":"IJSWIS.307908-11","unstructured":"Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014). Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572."},{"key":"IJSWIS.307908-12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2013.07.011"},{"key":"IJSWIS.307908-13","doi-asserted-by":"publisher","DOI":"10.4018\/IJSWIS.2019010106"},{"key":"IJSWIS.307908-14","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-7998-5071-7.ch007"},{"key":"IJSWIS.307908-15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1052"},{"key":"IJSWIS.307908-16","unstructured":"Lejun, G., Xiaolin, L., Zhihong, G., & Huakang, L. (2020). Extraction of drug interaction relationship based on bidirectional GRU and CNN [\u57fa\u4e8e\u53cc\u5411gru\u548ccnn\u7684\u836f\u7269\u76f8\u4e92\u4f5c\u7528\u5173\u7cfb\u62bd\u53d6]. Journal of Shaanxi Normal University (Natural Science Edition), 48(6), 6. http:\/\/qikan.cqvip.com\/Qikan\/Article\/Detail?id=710332435"},{"key":"IJSWIS.307908-17","unstructured":"Li, S., Xu, H., & Lu, Z. (2018). Generalize symbolic knowledge with neural rule engine. arXiv preprint arXiv:1808.10326."},{"key":"IJSWIS.307908-18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1129"},{"key":"IJSWIS.307908-19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-61951-0_6"},{"key":"IJSWIS.307908-20","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). Roberta: A robustly optimized BERT pre-training approach. arXiv preprint arXiv:1907.11692."},{"key":"IJSWIS.307908-21","doi-asserted-by":"publisher","DOI":"10.4018\/IJSWIS.2020040101"},{"key":"IJSWIS.307908-22","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM52615.2021.9669319"},{"key":"IJSWIS.307908-23","doi-asserted-by":"crossref","unstructured":"Miwa, M., & Bansal, M. (2016). End-to-end relation extraction using LSTMs on sequences and tree structures meeting of the association for computational linguistics. arXiv preprint arXiv:1601.00770.","DOI":"10.18653\/v1\/P16-1105"},{"key":"IJSWIS.307908-24","unstructured":"Ningthoujam, D., Yadav, S., Bhattacharyya, P., & Ekbal, A. (2019). Relation extraction between the clinical entities based on the shortest dependency path based lstm."},{"key":"IJSWIS.307908-25","unstructured":"Pawar, S., Palshikar, G. K., & Bhattacharyya, P. (2017). Relation extraction: A survey."},{"key":"IJSWIS.307908-26","doi-asserted-by":"publisher","DOI":"10.4018\/IJSWIS.2015070101"},{"key":"IJSWIS.307908-27","unstructured":"Soares, L., FitzGerald, N., Ling, J., & Kwiatkowski, T. (2019). Matching the Blanks: Distributional Similarity for Relation Learning meeting of the association for computational linguistics. arXiv preprint arXiv:1906.03158."},{"key":"IJSWIS.307908-28","doi-asserted-by":"crossref","unstructured":"Srinivasan, S., & L D, D. B. (2019). A parallel neural network approach for faster rumor identification in online social networks. International Journal on Semantic Web and Information Systems, 15(4), 69-89. http:\/\/DOI.org\/10.4018\/IJSWIS.2019100105","DOI":"10.4018\/IJSWIS.2019100105"},{"key":"IJSWIS.307908-29","article-title":"Biomedical named entity recognition using BERT in the machine reading comprehension framework.","volume":"118","author":"C.Sun","year":"2021","journal-title":"Journal of Biomedical Informatics"},{"issue":"5","key":"IJSWIS.307908-30","doi-asserted-by":"crossref","first-page":"8968","DOI":"10.1609\/aaai.v34i05.6428","article-title":"Ernie 2.0: A continual pre-training framework for language understanding.","volume":"34","author":"Y.Sun","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"IJSWIS.307908-31","doi-asserted-by":"crossref","unstructured":"Taewijit, S. (2021). Learning Pattern Relation-Based Hyperbolic Embedding for Adverse Drug Reaction Extraction. International Journal of Knowledge and Systems Science.","DOI":"10.4018\/IJKSS.2021040105"},{"key":"IJSWIS.307908-32","doi-asserted-by":"crossref","unstructured":"Tiktinsky, A., Viswanathan, V., Niezni, D., Azagury, D. M., Shamay, Y., Taub-Tabib, H., Hope, T., & Goldberg, Y. (2022). A Dataset for N-ary Relation Extraction of Drug Combinations. ArXiv, abs\/2205.02289.","DOI":"10.18653\/v1\/2022.naacl-main.233"},{"key":"IJSWIS.307908-33","first-page":"30","article-title":"Attention is all you need.","author":"A.Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"IJSWIS.307908-34","doi-asserted-by":"crossref","first-page":"18","DOI":"10.4018\/IJNCR.2020010103","article-title":"Comprehensive Review on Deep Learning for Neuronal Disorders: Applications of Deep Learning.","volume":"9","author":"V.Majhi","year":"2020","journal-title":"International Journal of Natural Computing Research"},{"key":"IJSWIS.307908-35","first-page":"616","article-title":"Learning to learn: Model regression networks for easy small sample learning.","author":"Y. X.Wang","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"IJSWIS.307908-36","doi-asserted-by":"crossref","unstructured":"Wei, Z., Su, J., Wang, Y., Tian, Y., & Chang, Y. (2020). A novel cascade binary tagging framework for relational triple extraction. rXiv preprint arXiv:1909.03227.","DOI":"10.18653\/v1\/2020.acl-main.136"},{"key":"IJSWIS.307908-37","doi-asserted-by":"crossref","unstructured":"Wu, S., & He, Y. (2019). Enriching pre-trained language model with entity information for relation classification. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management (pp. 2361-2364). ACM.","DOI":"10.1145\/3357384.3358119"},{"issue":"4-5","key":"IJSWIS.307908-38","first-page":"1004","article-title":"Joint extraction method of entity and relationship based on pointer network.","volume":"38","author":"W.Yongchao","year":"2021","journal-title":"Computer Application Research"},{"key":"IJSWIS.307908-39","unstructured":"Zeng, D., Liu, K., Lai, S., Zhou, G., & Zhao, J. (2014, August). Relation classification via convolutional deep neural network. In Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers (pp. 2335-2344). Academic Press."},{"issue":"10","key":"IJSWIS.307908-40","first-page":"77","article-title":"Medical entity relation extraction based on deep neural network and self-attention mechanism [\u57fa\u4e8e\u6df1\u5ea6\u795e\u7ecf\u7f51\u7edc\u548c\u81ea\u6ce8\u610f\u529b\u673a\u5236\u7684\u533b\u5b66\u5b9e\u4f53\u5173\u7cfb\u62bd\u53d6].","volume":"48","author":"S. H.Zhang","year":"2021","journal-title":"Computer Science"},{"key":"IJSWIS.307908-41","doi-asserted-by":"crossref","unstructured":"Zheng, H., Wen, R., Chen, X., Yang, Y., Zhang, Y., Zhang, Z. Z., Zhang, N., Qin, B., Xu, M., & Zheng, Y. (2021). PRGC: Potential relation and global correspondence based joint relational triple extraction. arXiv preprint arXiv:2106.09895.","DOI":"10.18653\/v1\/2021.acl-long.486"},{"key":"IJSWIS.307908-42","doi-asserted-by":"crossref","unstructured":"Zhou, P., Shi, W., Tian, J., Qi, Z., Li, B., Hao, H., & Xu, B. (2016). Attention-based bidirectional long short-term memory networks for relation classification. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics(Volume 2: Short Papers) (pp. 207-212). Academic Press.","DOI":"10.18653\/v1\/P16-2034"},{"key":"IJSWIS.307908-43","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Li, J., Zhao, Q., Wei, Y. C., & Jia, Y. (2021, July). Medical named entity recognition of Chinese electronic medical records based on stacked bidirectional long short-term memory. In 2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC) (pp. 1930-1935). IEEE.","DOI":"10.1109\/COMPSAC51774.2021.00293"}],"container-title":["International Journal on Semantic Web and Information Systems"],"original-title":[],"language":"ng","link":[{"URL":"https:\/\/www.igi-global.com\/viewtitle.aspx?TitleId=307908","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T18:16:32Z","timestamp":1692382592000},"score":1,"resource":{"primary":{"URL":"https:\/\/services.igi-global.com\/resolvedoi\/resolve.aspx?doi=10.4018\/IJSWIS.307908"}},"subtitle":[""],"short-title":[],"issued":{"date-parts":[[2022,8,12]]},"references-count":44,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,1]]}},"URL":"https:\/\/doi.org\/10.4018\/ijswis.307908","relation":{},"ISSN":["1552-6283","1552-6291"],"issn-type":[{"value":"1552-6283","type":"print"},{"value":"1552-6291","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,12]]}}}