{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T23:05:50Z","timestamp":1763161550456,"version":"3.45.0"},"publisher-location":"Singapore","reference-count":18,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819545742"},{"type":"electronic","value":"9789819545759"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-95-4575-9_13","type":"book-chapter","created":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T17:57:21Z","timestamp":1762711041000},"page":"190-200","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ClinAug: Closing the\u00a0Performance Gap in\u00a0Medical Error Detection with\u00a0Low-Cost Augmentation and\u00a0ClinicalBERT"],"prefix":"10.1007","author":[{"given":"Junli","family":"Dai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuming","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Farhaan","family":"Mirza","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"13_CR1","doi-asserted-by":"publisher","unstructured":"Abacha, A.B., et al.: Medec: a benchmark for medical error detection and correction in clinical notes. arXiv preprint arXiv:2412.19260 (2025). https:\/\/doi.org\/10.48550\/arXiv.2412.19260","DOI":"10.48550\/arXiv.2412.19260"},{"key":"13_CR2","doi-asserted-by":"publisher","unstructured":"Ben Abacha, A., Yim, W.-W., Fu, Y., Sun, Z., Xia, F., Yetisgen, M.: Overview of the mediqa-corr 2024 shared task on medical error detection and correction. In: Proceedings of the 6th Clinical Natural Language Processing Workshop, pp. 596\u2013603 (2024). https:\/\/doi.org\/10.18653\/v1\/2024.clinicalnlp-1.57","DOI":"10.18653\/v1\/2024.clinicalnlp-1.57"},{"issue":"1","key":"13_CR3","doi-asserted-by":"publisher","first-page":"13854","DOI":"10.1038\/s41598-025-98281-9","volume":"15","author":"X Chen","year":"2025","unstructured":"Chen, X., Du, Y.: Enhancing medical text classification with gan-based data augmentation and multi-task learning in bert. Sci. Rep. 15(1), 13854 (2025). https:\/\/doi.org\/10.1038\/s41598-025-98281-9","journal-title":"Sci. Rep."},{"key":"13_CR4","doi-asserted-by":"publisher","unstructured":"Dai, X., Adel, H.: An analysis of simple data augmentation for named entity recognition. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 3861\u20133867 (2020). https:\/\/doi.org\/10.18653\/v1\/2020.coling-main.343","DOI":"10.18653\/v1\/2020.coling-main.343"},{"issue":"1","key":"13_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3458754","volume":"3","author":"Y Gu","year":"2022","unstructured":"Gu, Y., et al.: Domain-specific language model pretraining for biomedical natural language processing. ACM Trans. Comput. Healthcare 3(1), 1\u201323 (2022). https:\/\/doi.org\/10.1145\/3458754","journal-title":"ACM Trans. Comput. Healthcare"},{"key":"13_CR6","doi-asserted-by":"publisher","unstructured":"Huang, K., Altosaar, J., Ranganath, R.: Clinicalbert: modeling clinical notes and predicting hospital readmission. arXiv preprint arXiv:1904.05342 (2020). https:\/\/doi.org\/10.48550\/arXiv.1904.05342","DOI":"10.48550\/arXiv.1904.05342"},{"key":"13_CR7","doi-asserted-by":"publisher","unstructured":"Koontz, J., Oronoz, M., P\u00e9rez, A.: Evaluating data augmentation for medication identification in clinical notes. In: Proceedings of the Conference Recent Advances in Natural Language Processing - Large Language Models for Natural Language processing, pp. 578\u2013585 (2023). https:\/\/doi.org\/10.26615\/978-954-452-092-2_063","DOI":"10.26615\/978-954-452-092-2_063"},{"issue":"4","key":"13_CR8","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2020","unstructured":"Lee, J., et al.: Biobert: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 36(4), 1234\u20131240 (2020). https:\/\/doi.org\/10.1093\/bioinformatics\/btz682","journal-title":"Bioinformatics"},{"issue":"1","key":"13_CR9","doi-asserted-by":"publisher","first-page":"19587","DOI":"10.1038\/s41598-023-45946-y","volume":"13","author":"TV Nguyen","year":"2023","unstructured":"Nguyen, T.V., et al.: Efficient automated error detection in medical data using deep-learning and label-clustering. Sci. Rep. 13(1), 19587 (2023). https:\/\/doi.org\/10.1038\/s41598-023-45946-y","journal-title":"Sci. Rep."},{"key":"13_CR10","unstructured":"Ollagnier, A., Williams, H.: Text augmentation techniques for clinical case classification. Technical Report (2020)"},{"key":"13_CR11","doi-asserted-by":"publisher","unstructured":"Pajaro, J., Puertas, E., Villate, D., Estrada, L., Tinjaca, L.: Verbanexai at mediqa-corr: efficacy of gru with biowordvec and clinicalbert in error correction in clinical notes. In: Proceedings of the 6th Clinical Natural Language Processing Workshop, pp. 461\u2013469 (2024). https:\/\/doi.org\/10.18653\/v1\/2024.clinicalnlp-1.46","DOI":"10.18653\/v1\/2024.clinicalnlp-1.46"},{"key":"13_CR12","doi-asserted-by":"publisher","unstructured":"Sarker, S., Qian, L., Dong, X.: Medical data augmentation via chatgpt: a case study on medication identification and medication event classification. arXiv preprint arXiv:2306.07297 (2023). https:\/\/doi.org\/10.48550\/arXiv.2306.07297","DOI":"10.48550\/arXiv.2306.07297"},{"issue":"1","key":"13_CR13","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1186\/s40537-021-00492-0","volume":"8","author":"C Shorten","year":"2021","unstructured":"Shorten, C., Khoshgoftaar, T.M., Furht, B.: Text data augmentation for deep learning. J. Big Data 8(1), 101 (2021). https:\/\/doi.org\/10.1186\/s40537-021-00492-0","journal-title":"J. Big Data"},{"key":"13_CR14","doi-asserted-by":"publisher","unstructured":"Sun, Z., Yim, W.-W., Uzuner, \u00d6., Xia, F., Yetisgen, M.: A scoping review of natural language processing in addressing medically inaccurate information: errors, misinformation, and hallucination. arXiv preprint arXiv:2505.00008 (2025). https:\/\/doi.org\/10.48550\/arXiv.2505.00008","DOI":"10.48550\/arXiv.2505.00008"},{"key":"13_CR15","doi-asserted-by":"publisher","unstructured":"Toma, A., Xie, R., Palayew, S., Lawler, P.R., Wang, B.: Wanglab at mediqa-corr 2024: optimized llm-based programs for medical error detection and correction. arXiv preprint arXiv:2404.14544 (2024). https:\/\/doi.org\/10.48550\/arXiv.2404.14544","DOI":"10.48550\/arXiv.2404.14544"},{"key":"13_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.128151","volume":"286","author":"C Woolsey","year":"2025","unstructured":"Woolsey, C., Leroy, G., Maltman, N.: Enhancing text datasets with scaling and targeting data augmentation to improve bert-based machine learners. Expert Syst. Appl. 286, 128151 (2025). https:\/\/doi.org\/10.1016\/j.eswa.2025.128151","journal-title":"Expert Syst. Appl."},{"issue":"1","key":"13_CR17","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1038\/s41746-022-00742-2","volume":"5","author":"X Yang","year":"2022","unstructured":"Yang, X., Chen, A., PourNejatian, N., Shin, H.C., Smith, K.E., Parisien, C., et al.: A large language model for electronic health records. NPJ Dig. Med. 5(1), 194 (2022). https:\/\/doi.org\/10.1038\/s41746-022-00742-2","journal-title":"NPJ Dig. Med."},{"key":"13_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2022.104066","volume":"129","author":"Y Zhu","year":"2022","unstructured":"Zhu, Y., Wang, X., Guan, Z., Zhang, M.: Enhancing clinical named entity recognition and relation extraction with medical knowledge. J. Biomed. Inf. 129, 104066 (2022). https:\/\/doi.org\/10.1016\/j.jbi.2022.104066","journal-title":"J. Biomed. Inf."}],"container-title":["Communications in Computer and Information Science","Knowledge Management and Acquisition for Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4575-9_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T23:02:10Z","timestamp":1763161330000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4575-9_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819545742","9789819545759"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4575-9_13","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"10 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PKAW","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Principle and Practice of Data and Knowledge Acquisition Workshop","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wellington","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pkaw2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pkawwebsite.github.io\/2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}