{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T17:45:14Z","timestamp":1790358314773,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591957","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:59Z","timestamp":1689726179000},"page":"1853-1858","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["BioAug: Conditional Generation based Data Augmentation for Low-Resource Biomedical NER"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3773-561X","authenticated-orcid":false,"given":"Sreyan","family":"Ghosh","sequence":"first","affiliation":[{"name":"University of Maryland College Park, USA, College Park, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1831-7709","authenticated-orcid":false,"given":"Utkarsh","family":"Tyagi","sequence":"additional","affiliation":[{"name":"University of Maryland College Park, USA, College Park, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5516-3060","authenticated-orcid":false,"given":"Sonal","family":"Kumar","sequence":"additional","affiliation":[{"name":"University of Maryland College Park, USA, College Park, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7047-9801","authenticated-orcid":false,"given":"Dinesh","family":"Manocha","sequence":"additional","affiliation":[{"name":"University of Maryland College Park, USA, College Park, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_2_1_1","first-page":"19","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations). Association for Computational Linguistics","author":"Akbik Alan","year":"2019","unstructured":"Alan Akbik, Tanja Bergmann, Duncan Blythe, Kashif Rasul, Stefan Schweter, and Roland Vollgraf. 2019. FLAIR: An Easy-to-Use Framework for State-of-the-Art NLP. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations). Association for Computational Linguistics, Minneapolis, Minnesota, 54--59. https:\/\/doi.org\/10. 18653\/v1\/N19-4010"},{"key":"e_1_3_2_2_2_1","volume-title":"Proceedings of the 45th annual meeting of the association of computational linguistics. 576--583","author":"Bunescu Razvan","year":"2007","unstructured":"Razvan Bunescu and Raymond Mooney. 2007. Learning to extract relations from the web using minimal supervision. In Proceedings of the 45th annual meeting of the association of computational linguistics. 576--583."},{"key":"e_1_3_2_2_3_1","volume-title":"An empirical survey of data augmentation for limited data learning in NLP. arXiv preprint arXiv:2106.07499","author":"Chen Jiaao","year":"2021","unstructured":"Jiaao Chen, Derek Tam, Colin Raffel, Mohit Bansal, and Diyi Yang. 2021. An empirical survey of data augmentation for limited data learning in NLP. arXiv preprint arXiv:2106.07499 (2021)."},{"key":"e_1_3_2_2_4_1","volume-title":"Proceedings of the International Joint Workshop on Natural Language Processing in Biomedicine and its Applications (NLPBA\/BioNLP). 73--78","author":"Collier Nigel","year":"2004","unstructured":"Nigel Collier and Jin-Dong Kim. 2004. Introduction to the bio-entity recognition task at JNLPBA. In Proceedings of the International Joint Workshop on Natural Language Processing in Biomedicine and its Applications (NLPBA\/BioNLP). 73--78."},{"key":"e_1_3_2_2_5_1","volume-title":"An analysis of simple data augmentation for named entity recognition. arXiv preprint arXiv:2010.11683","author":"Dai Xiang","year":"2020","unstructured":"Xiang Dai and Heike Adel. 2020. An analysis of simple data augmentation for named entity recognition. arXiv preprint arXiv:2010.11683 (2020)."},{"key":"e_1_3_2_2_6_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_7_1","volume-title":"Shafiq Joty, Luo Si, and Chunyan Miao.","author":"Ding Bosheng","year":"2020","unstructured":"Bosheng Ding, Linlin Liu, Lidong Bing, Canasai Kruengkrai, Thien Hai Nguyen, Shafiq Joty, Luo Si, and Chunyan Miao. 2020. DAGA: Data augmentation with a generation approach for low-resource tagging tasks. arXiv preprint arXiv:2011.01549 (2020)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2013.12.006"},{"key":"e_1_3_2_2_9_1","volume-title":"A survey of data augmentation approaches for NLP. arXiv preprint arXiv:2105.03075","author":"Feng Steven Y","year":"2021","unstructured":"Steven Y Feng, Varun Gangal, Jason Wei, Sarath Chandar, Soroush Vosoughi, Teruko Mitamura, and Eduard Hovy. 2021. A survey of data augmentation approaches for NLP. arXiv preprint arXiv:2105.03075 (2021)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2017.05.002"},{"key":"e_1_3_2_2_11_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning (ICML'20)","author":"Guu Kelvin","year":"2020","unstructured":"Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Ming-Wei Chang. 2020. REALM: Retrieval-Augmented Language Model Pre-Training. In Proceedings of the 37th International Conference on Machine Learning (ICML'20). JMLR.org, Article 368, 10 pages."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-3029"},{"key":"e_1_3_2_2_13_1","volume-title":"Andrew Bartko, and Chun-Nan Hsu.","author":"Hogan William","year":"2021","unstructured":"William Hogan, Molly Huang, Yannis Katsis, Tyler Baldwin, Ho-Cheol Kim, Yoshiki Vazquez Baeza, Andrew Bartko, and Chun-Nan Hsu. 2021. Abstractified multi-instance learning (amil) for biomedical relation extraction. arXiv preprint arXiv:2110.12501 (2021)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.2016299"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1236"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaa309"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2920708"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3157854"},{"key":"e_1_3_2_2_20_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68763-2_48"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1186\/1758-2946-7-S1-S1"},{"key":"e_1_3_2_2_23_1","volume-title":"Biocomputing","author":"Leaman Robert","year":"2008","unstructured":"Robert Leaman and Graciela Gonzalez. 2008. BANNER: an executable survey of advances in biomedical named entity recognition. In Biocomputing 2008. World Scientific, 652--663."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"e_1_3_2_2_25_1","volume-title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461","author":"Lewis Mike","year":"2019","unstructured":"Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. 2019. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)."},{"key":"e_1_3_2_2_26_1","volume-title":"Carolyn J Mattingly, Thomas C Wiegers, and Zhiyong Lu.","author":"Li Jiao","year":"2016","unstructured":"Jiao Li, Yueping Sun, Robin J Johnson, Daniela Sciaky, Chih-Hsuan Wei, Robert Leaman, Allan Peter Davis, Carolyn J Mattingly, Thomas C Wiegers, and Zhiyong Lu. 2016. BioCreative V CDR task corpus: a resource for chemical disease relation extraction. Database 2016 (2016)."},{"key":"e_1_3_2_2_27_1","volume-title":"The unified medical language system. Yearbook of medical informatics 2, 01","author":"Lindberg Donald AB","year":"1993","unstructured":"Donald AB Lindberg, Betsy L Humphreys, and Alexa T McCray. 1993. The unified medical language system. Yearbook of medical informatics 2, 01 (1993), 41--51."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.453"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.3390\/info6040790"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btx761"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib"},{"key":"e_1_3_2_2_32_1","volume-title":"The NCBI handbook. Bethesda (MD): National Center for Biotechnology Information (US)","author":"McEntyre Jo","year":"2002","unstructured":"Jo McEntyre and Jim Ostell. 2002. The NCBI handbook. Bethesda (MD): National Center for Biotechnology Information (US) (2002)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-5034"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1019"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.bionlp-1.12"},{"key":"e_1_3_2_2_36_1","volume-title":"Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition. arXiv preprint cs\/0306050","author":"Sang Erik F","year":"2003","unstructured":"Erik F Sang and Fien De Meulder. 2003. Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition. arXiv preprint cs\/0306050 (2003)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"crossref","unstructured":"Larry Smith Lorraine K Tanabe Cheng-Ju Kuo I Chung Chun-Nan Hsu Yu-Shi Lin Roman Klinger Christoph M Friedrich Kuzman Ganchev Manabu Torii et al. 2008. Overview of BioCreative II gene mention recognition. Genome biology 9 2 (2008) 1--19.","DOI":"10.1186\/gb-2008-9-s2-s2"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746482"},{"key":"e_1_3_2_2_39_1","volume-title":"A clinical text classification paradigm using weak supervision and deep representation. BMC medical informatics and decision making 19","author":"Wang Yanshan","year":"2019","unstructured":"Yanshan Wang, Sunghwan Sohn, Sijia Liu, Feichen Shen, Liwei Wang, Elizabeth J Atkinson, Shreyasee Amin, and Hongfang Liu. 2019. A clinical text classification paradigm using weak supervision and deep representation. BMC medical informatics and decision making 19 (2019), 1--13."},{"key":"e_1_3_2_2_40_1","volume-title":"The Effectiveness of Masked Language Modeling and Adapters for Factual Knowledge Injection. arXiv preprint arXiv:2210.00907","author":"Wold Sondre","year":"2022","unstructured":"Sondre Wold. 2022. The Effectiveness of Masked Language Modeling and Adapters for Factual Knowledge Injection. arXiv preprint arXiv:2210.00907 (2022)."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.bionlp-1.9"},{"key":"e_1_3_2_2_42_1","volume-title":"SMedBERT: A knowledge-enhanced pre-trained language model with structured semantics for medical text mining. arXiv preprint arXiv:2108.08983","author":"Zhang Taolin","year":"2021","unstructured":"Taolin Zhang, Zerui Cai, Chengyu Wang, Minghui Qiu, Bite Yang, and Xiaofeng He. 2021. SMedBERT: A knowledge-enhanced pre-trained language model with structured semantics for medical text mining. arXiv preprint arXiv:2108.08983 (2021)."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.160"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"crossref","unstructured":"Wenxuan Zhou and Muhao Chen. 2021. Learning from noisy labels for entity-centric information extraction. arXiv preprint arXiv:2104.08656 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.437"}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Taipei Taiwan","acronym":"SIGIR '23","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591957","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591957","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:38:08Z","timestamp":1750178288000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591957"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":45,"alternative-id":["10.1145\/3539618.3591957","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591957","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}