{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T03:50:19Z","timestamp":1761709819813,"version":"3.41.0"},"reference-count":32,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2021,1,4]],"date-time":"2021-01-04T00:00:00Z","timestamp":1609718400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000092","name":"U.S. National Library of Medicine","doi-asserted-by":"publisher","award":["R21LM012274"],"award-info":[{"award-number":["R21LM012274"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006108","name":"National Center for Advancing Translational Sciences","doi-asserted-by":"publisher","award":["UL1TR001998"],"award-info":[{"award-number":["UL1TR001998"]}],"id":[{"id":"10.13039\/100006108","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Comput. Healthcare"],"published-print":{"date-parts":[[2021,4,30]]},"abstract":"<jats:p>Preventable adverse events as a result of medical errors present a growing concern in the healthcare system. As drug-drug interactions (DDIs) may lead to preventable adverse events, being able to extract DDIs from drug labels into a machine-processable form is an important step toward effective dissemination of drug safety information. Herein, we tackle the problem of jointly extracting mentions of drugs and their interactions, including interaction<jats:italic>outcome<\/jats:italic>, from drug labels. Our deep learning approach entails composing various intermediate representations, including graph-based context derived using graph convolutions (GCs) with a novel attention-based gating mechanism (holistically called GCA), which are combined in meaningful ways to predict on all subtasks jointly. Our model is trained and evaluated on the 2018 TAC DDI corpus. Our GCA model in conjunction with transfer learning performs at 39.20% F1 and 26.09% F1 on entity recognition (ER) and relation extraction (RE), respectively, on the first official test set and at 45.30% F1 and 27.87% F1 on ER and RE, respectively, on the second official test set. These updated results lead to improvements over our prior best by up to 6 absolute F1 points. After controlling for available training data, the proposed model exhibits state-of-the-art performance for this task.<\/jats:p>","DOI":"10.1145\/3423209","type":"journal-article","created":{"date-parts":[[2021,1,4]],"date-time":"2021-01-04T14:42:32Z","timestamp":1609771352000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Attention-Gated Graph Convolutions for Extracting Drug Interaction Information from Drug Labels"],"prefix":"10.1145","volume":"2","author":[{"given":"Tung","family":"Tran","sequence":"first","affiliation":[{"name":"University of Kentucky, United States, Lexington, KY"}]},{"given":"Ramakanth","family":"Kavuluru","sequence":"additional","affiliation":[{"name":"University of Kentucky, United States, Lexington, KY"}]},{"given":"Halil","family":"Kilicoglu","sequence":"additional","affiliation":[{"name":"National Library of Medicine, Bethesda, MD, United States"}]}],"member":"320","published-online":{"date-parts":[[2021,1,4]]},"reference":[{"volume-title":"Globally normalized transition-based neural networks. arXiv preprint arXiv:1603.06042","year":"2016","author":"Andor Daniel","key":"e_1_2_1_1_1"},{"volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 680--685","year":"2018","author":"Asada Masaki","key":"e_1_2_1_2_1"},{"volume-title":"Proceedings of 3th International Conference on Learning Representations (ICLR\u201915)","year":"2015","author":"Bahdanau Dzmitry","key":"e_1_2_1_3_1"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00104"},{"volume-title":"Proceedings of the 2018 Text Analysis Conference (TAC\u201918)","year":"2018","author":"Dandala Bharath","key":"e_1_2_1_5_1"},{"volume-title":"Overview of the TAC 2018 drug-drug interaction extraction from drug labels track. In Proceedings of the 2018 Text Analysis Conference (TAC\u201918)","year":"2018","author":"Demner-Fushman Dina","key":"e_1_2_1_6_1"},{"volume-title":"Proceedings of the 17th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.","year":"2018","author":"Devlin Jacob","key":"e_1_2_1_7_1"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2013.07.011"},{"key":"e_1_2_1_10_1","volume-title":"IJCAI-99 Workshop on Text Mining: Foundations, Techniques and Applications","volume":"1","author":"Jones Rosie","year":"1999"},{"volume-title":"5th IEEE International Conference on Healthcare Informatics (ICHI\u201917)","year":"2017","author":"Kavuluru Ramakanth","key":"e_1_2_1_11_1"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btg1023"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"volume-title":"Donaldson","year":"2000","author":"Kohn Linda T.","key":"e_1_2_1_14_1"},{"key":"e_1_2_1_15_1","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","article-title":"BioBERT: A pre-trained biomedical language representation model for biomedical text mining","volume":"36","author":"Lee Jinhyuk","year":"2020","journal-title":"Bioinformatics"},{"volume-title":"Adverse events in hospitals: National incidence among Medicare beneficiaries","author":"Levinson Daniel R.","key":"e_1_2_1_16_1"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-017-1609-9"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0190926"},{"volume-title":"2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM\u201916)","year":"2016","author":"Liu Shengyu","key":"e_1_2_1_19_1"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/4310634"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbw001"},{"volume-title":"Proceedings of 5th International Symposium on Languages in Biology and Medicine. 39--44","year":"2013","author":"Pyysalo Sampo","key":"e_1_2_1_22_1"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.3115\/1596374.1596399"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2018.08.005"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/3019233"},{"key":"e_1_2_1_26_1","first-page":"1","article-title":"Exploring convolutional neural networks for drug--drug interaction extraction","volume":"2017","author":"Su\u00e1rez-Paniagua V\u00edctor","year":"2017","journal-title":"Database"},{"key":"e_1_2_1_27_1","doi-asserted-by":"crossref","first-page":"37","DOI":"10.3390\/e21010037","article-title":"Drug-drug interaction extraction via recurrent hybrid convolutional neural networks with an improved focal loss","volume":"21","author":"Sun Xia","year":"2019","journal-title":"Entropy"},{"volume-title":"Proceedings of the 2018 Text Analysis Conference (TAC\u201918)","year":"2018","author":"Tang Siliang","key":"e_1_2_1_28_1"},{"volume-title":"Proceedings of the 2018 Text Analysis Conference (TAC\u201918)","year":"2018","author":"Tran Tung","key":"e_1_2_1_29_1"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1054010"},{"volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.","author":"Zhang Yuhao","key":"e_1_2_1_31_1"},{"key":"e_1_2_1_32_1","doi-asserted-by":"crossref","first-page":"3444","DOI":"10.1093\/bioinformatics\/btw486","article-title":"Drug drug interaction extraction from biomedical literature using syntax convolutional neural network","volume":"32","author":"Zhao Zhehuan","year":"2016","journal-title":"Bioinformatics"}],"container-title":["ACM Transactions on Computing for Healthcare"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3423209","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3423209","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:24:57Z","timestamp":1750195497000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3423209"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,4]]},"references-count":32,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,4,30]]}},"alternative-id":["10.1145\/3423209"],"URL":"https:\/\/doi.org\/10.1145\/3423209","relation":{},"ISSN":["2691-1957","2637-8051"],"issn-type":[{"type":"print","value":"2691-1957"},{"type":"electronic","value":"2637-8051"}],"subject":[],"published":{"date-parts":[[2021,1,4]]},"assertion":[{"value":"2019-10-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-09-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-01-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}