{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T08:11:06Z","timestamp":1777882266197,"version":"3.51.4"},"reference-count":97,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100024370","name":"Ministero dell'Istruzione dell'Universit\u00e0 e della Ricerca","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100024370","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007706","name":"Ministero dello Sviluppo Economico","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007706","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007385","name":"Fondazione Cassa di Risparmio in Bologna","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007385","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.eswa.2026.131725","type":"journal-article","created":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T23:10:08Z","timestamp":1772320208000},"page":"131725","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["OpenBioNER-v2: A suite of lightweight models for zero-shot medical named entity recognition via type descriptions"],"prefix":"10.1016","volume":"318","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1507-1354","authenticated-orcid":false,"given":"Alessio","family":"Cocchieri","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9845-0231","authenticated-orcid":false,"given":"Giacomo","family":"Frisoni","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2987-6206","authenticated-orcid":false,"given":"Francesco","family":"Zangrillo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3574-9962","authenticated-orcid":false,"given":"Luca","family":"Ragazzi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8646-7354","authenticated-orcid":false,"given":"Marcos Mart\u00ednez","family":"Galindo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9221-4633","authenticated-orcid":false,"given":"Giuseppe","family":"Tagliavini","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3663-7877","authenticated-orcid":false,"given":"Gianluca","family":"Moro","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.131725_bib0001","unstructured":"Abdul, W. M., Pimentel, M. A. F., Salman, M. U., Raha, T., Christophe, C., Kanithi, P. K., Hayat, N., Rajan, R., & Khan, S. (2024). Named clinical entity recognition benchmark. https:\/\/arxiv.org\/abs\/2410.05046."},{"key":"10.1016\/j.eswa.2026.131725_bib0002","series-title":"Proceedings of the 2022 conference on empirical methods in natural language processing, EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7\u201311, 2022","first-page":"1998","article-title":"Large language models are few-shot clinical information extractors","author":"Agrawal","year":"2022"},{"key":"10.1016\/j.eswa.2026.131725_bib0003","doi-asserted-by":"crossref","unstructured":"Alsentzer, E., Murphy, J. R., Boag, W., Weng, W., Jin, D., Naumann, T., & McDermott, M. B. A. (2019). Publicly available clinical BERT embeddings. http:\/\/arxiv.org\/abs\/1904.03323.","DOI":"10.18653\/v1\/W19-1909"},{"issue":"17","key":"10.1016\/j.eswa.2026.131725_bib0004","doi-asserted-by":"crossref","first-page":"2723","DOI":"10.1093\/bioinformatics\/btx275","article-title":"Neuro-symbolic representation learning on biological knowledge graphs","volume":"33","author":"Alshahrani","year":"2017","journal-title":"Bioinform."},{"issue":"1","key":"10.1016\/j.eswa.2026.131725_bib0005","doi-asserted-by":"crossref","first-page":"3852","DOI":"10.1038\/s41598-025-86890-3","article-title":"Evaluating GPT models for clinical note de-identification","volume":"15","author":"Altalla\u2019","year":"2025","journal-title":"Scientific Reports"},{"key":"10.1016\/j.eswa.2026.131725_sbref0006","series-title":"Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing (volume 1: Long papers)","first-page":"1516","article-title":"Leveraging type descriptions for zero-shot named entity recognition and classification","author":"Aly","year":"2021"},{"key":"10.1016\/j.eswa.2026.131725_sbref0007","series-title":"AMIA 2001, american medical informatics association annual symposium, Washington, DC, USA, November 3\u20137, 2001","article-title":"Effective mapping of biomedical text to the UMLS metathesaurus: the metamap program","author":"Aronson","year":"2001"},{"key":"10.1016\/j.eswa.2026.131725_sbref0008","series-title":"Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP)","first-page":"3615","article-title":"SciBERT: a pretrained language model for scientific text","author":"Beltagy","year":"2019"},{"key":"10.1016\/j.eswa.2026.131725_bib0009","series-title":"Proceedings of the 2024 conference on empirical methods in natural language processing","first-page":"11829","article-title":"NuNER: entity recognition encoder pre-training via LLM-annotated data","author":"Bogdanov","year":"2024"},{"key":"10.1016\/j.eswa.2026.131725_bib0010","series-title":"Proceedings of the twelfth ACM SIGKDD international conference on knowledge discovery and data mining, Philadelphia, PA, USA, August 20\u201323, 2006","first-page":"535","article-title":"Model compression","author":"Bucila","year":"2006"},{"key":"10.1016\/j.eswa.2026.131725_bib0011","series-title":"Proceedings of the 2024 conference on empirical methods in natural language processing","first-page":"12105","article-title":"Unknown claims: generation of fact-checking training examples from unstructured and structured data","author":"Bussotti","year":"2024"},{"key":"10.1016\/j.eswa.2026.131725_bib0012","series-title":"Proceedings of the 2021 conference of the north american chapter of the association for computational linguistics: Human language technologies","first-page":"3470","article-title":"ZS-BERT: Towards zero-shot relation extraction with attribute representation learning","author":"Chen","year":"2021"},{"key":"10.1016\/j.eswa.2026.131725_bib0013","article-title":"Med42-v2: A suite of clinical LLMs","author":"Christophe","year":"2024","journal-title":"CoRR abs\/2408.06142"},{"key":"10.1016\/j.eswa.2026.131725_sbref0014","first-page":"70:1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"Journal of Machine Learning Research : JMLR"},{"key":"10.1016\/j.eswa.2026.131725_bib0015","series-title":"Findings of the association for computational linguistics: NAACL 2025","first-page":"818","article-title":"OpenBioNER: Lightweight open-domain biomedical named entity recognition through entity type description","author":"Cocchieri","year":"2025"},{"key":"10.1016\/j.eswa.2026.131725_sbref0016","series-title":"Findings of the association for computational linguistics: ACL 2025","first-page":"15594","article-title":"ZeroNER: Fueling zero-shot named entity recognition via entity type descriptions","author":"Cocchieri","year":"2025"},{"key":"10.1016\/j.eswa.2026.131725_sbref0017","series-title":"Proceedings of the international joint workshop on natural language processing in biomedicine and its applications (NLPBA\/BioNLP)","first-page":"73","article-title":"Introduction to the bio-entity recognition task at JNLPBA","author":"Collier","year":"2004"},{"key":"10.1016\/j.eswa.2026.131725_sbref0018","series-title":"Proceedings of the 63rd annual meeting of the association for computational linguistics (volume 1: Long papers), ACL 2025, Vienna, Austria, July 27, - August 1, 2025","first-page":"19352","article-title":"A modular approach for clinical SLMs driven by synthetic data with pre-instruction tuning, model merging, and clinical-tasks alignment","author":"Corbeil","year":"2025"},{"issue":"4","key":"10.1016\/j.eswa.2026.131725_bib0019","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1093\/jamia\/ocw177","article-title":"Metamap lite: An evaluation of a new java implementation of metamap","volume":"24","author":"Demner-Fushman","year":"2017","journal-title":"The Journal of the American Medical Informatics Association"},{"key":"10.1016\/j.eswa.2026.131725_bib0020","series-title":"Proceedings of the 2019 conference of the north American chapter of the association for computational linguistics: Human language technologies, volume 1 (long and short papers)","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.eswa.2026.131725_bib0021","series-title":"Findings of the association for computational linguistics: ACL 2024","first-page":"3461","article-title":"Rethinking negative instances for generative named entity recognition","author":"Ding","year":"2024"},{"key":"10.1016\/j.eswa.2026.131725_bib0022","doi-asserted-by":"crossref","unstructured":"Ding, Z., Wei, W., & Fan, C. (2025). Selecting and merging: Towards adaptable and scalable named entity recognition with large language models. 10.48550\/ARXIV.2506.22813.","DOI":"10.18653\/v1\/2025.acl-long.487"},{"key":"10.1016\/j.eswa.2026.131725_bib0023","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jbi.2013.12.006","article-title":"NCBI Disease corpus: A resource for disease name recognition and concept normalization","volume":"47","author":"Dogan","year":"2014","journal-title":"The Journal of Biomedical Informatics"},{"key":"10.1016\/j.eswa.2026.131725_bib0024","series-title":"KDIR 2014 - proceedings of the international conference on knowledge discovery and information retrieval, Rome, Italy, 21 - 24 October, 2014","first-page":"107","article-title":"Discovering new gene functionalities from random perturbations of known gene ontological annotations","author":"Domeniconi","year":"2014"},{"key":"10.1016\/j.eswa.2026.131725_bib0025","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.cmpb.2015.12.002","article-title":"Cross-organism learning method to discover new gene functionalities","volume":"126","author":"Domeniconi","year":"2016","journal-title":"Computer Methods and Programs in Biomedicine"},{"key":"10.1016\/j.eswa.2026.131725_bib0026","unstructured":"Dubey, A., Jauhri, A., Pandey, A., Kadian, A., Al-Dahle, A., Letman, A., Mathur, A., Schelten, A., Yang, A., Fan, A., Goyal, A., Hartshorn, A., Yang, A., Mitra, A., Sravankumar, A., Korenev, A., Hinsvark, A., Rao, A., Zhang, A., Rodriguez, A., Gregerson, A., Spataru, A., Rozi\u00e8re, B., Biron, B., Tang, B., Chern, B., Caucheteux, C., Nayak, C., Bi, C., Marra, C., McConnell, C., Keller, C., Touret, C., Wu, C., Wong, C., Ferrer, C. C., Nikolaidis, C., Allonsius, D., Song, D., Pintz, D., Livshits, D., Esiobu, D., Choudhary, D., Mahajan, D., Garcia-Olano, D., Perino, D., Hupkes, D., Lakomkin, E., AlBadawy, E., Lobanova, E., Dinan, E., Smith, E. M., Radenovic, F., Zhang, F., Synnaeve, G., Lee, G., Anderson, G. L., Nail, G., Mialon, G., Pang, G., Cucurell, G., Nguyen, H., Korevaar, H., Xu, H., Touvron, H., Zarov, I., Ibarra, I. A., Kloumann, I. M., Misra, I., Evtimov, I., Copet, J., Lee, J., Geffert, J., Vranes, J., Park, J., Mahadeokar, J., Shah, J., van der Linde, J., Billock, J., Hong, J., Lee, J., Fu, J., Chi, J., Huang, J., Liu, J., Wang, J., Yu, J., Bitton, J., Spisak, J., Park, J., Rocca, J., Johnstun, J., Saxe, J., Jia, J., Alwala, K. V., Upasani, K., Plawiak, K., Li, K., Heafield, K. et al., et al. (2024). The llama 3 herd of models. 10.48550\/ARXIV.2407.21783."},{"key":"10.1016\/j.eswa.2026.131725_bib0027","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1186\/1472-6947-11-46","article-title":"The re-identification risk of Canadians from longitudinal demographics","volume":"11","author":"Emam","year":"2011","journal-title":"BMC Medical Informatics and Decision Making"},{"key":"10.1016\/j.eswa.2026.131725_bib0028","first-page":"12781","article-title":"Cogito ergo summ: Abstractive summarization of biomedical papers via semantic parsing graphs and consistency rewards","author":"Frisoni","year":"2023"},{"key":"10.1016\/j.eswa.2026.131725_bib0029","series-title":"Proceedings of the 2022 conference on empirical methods in natural language processing","first-page":"5770","article-title":"BioReader: A retrieval-enhanced text-to-text transformer for biomedical literature","author":"Frisoni","year":"2022"},{"key":"10.1016\/j.eswa.2026.131725_bib0030","doi-asserted-by":"crossref","first-page":"160721","DOI":"10.1109\/ACCESS.2021.3130956","article-title":"A survey on event extraction for natural language understanding: Riding the biomedical literature wave","volume":"9","author":"Frisoni","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2026.131725_bib0031","doi-asserted-by":"crossref","unstructured":"Fuente, N. D. L., Sainz, O., Garc\u00eda-Ferrero, I., & Agirre, E. (2025). Guidex: Guided synthetic data generation for zero-shot information extraction. 10.48550\/ARXIV.2506.00649.","DOI":"10.18653\/v1\/2025.findings-acl.1245"},{"key":"10.1016\/j.eswa.2026.131725_bib0032","unstructured":"Gao, L., Biderman, S., Black, S., Golding, L., Hoppe, T., Foster, C., Phang, J., He, H., Thite, A., Nabeshima, N., Presser, S., & Leahy, C. (2021). The pile: An 800GB dataset of diverse text for language modeling. https:\/\/arxiv.org\/abs\/2101.00027."},{"key":"10.1016\/j.eswa.2026.131725_bib0033","unstructured":"Garg, M., Raza, S., Rayana, S., Liu, X., & Sohn, S. (2025). The rise of small language models in healthcare: A comprehensive survey. 10.48550\/ARXIV.2504.17119."},{"issue":"23","key":"10.1016\/j.eswa.2026.131725_bib0034","doi-asserted-by":"crossref","first-page":"4087","DOI":"10.1093\/bioinformatics\/bty449","article-title":"Transfer learning for biomedical named entity recognition with neural networks","volume":"34","author":"Giorgi","year":"2018","journal-title":"Bioinformatics"},{"key":"10.1016\/j.eswa.2026.131725_bib0035","series-title":"Proceedings of the 2006\u202fACM workshop on privacy in the electronic society, WPES 2006, Alexandria, VA, USA, October 30, 2006","first-page":"77","article-title":"Revisiting the uniqueness of simple demographics in the US population","author":"Golle","year":"2006"},{"issue":"1","key":"10.1016\/j.eswa.2026.131725_bib0036","doi-asserted-by":"crossref","first-page":"2:1","DOI":"10.1145\/3458754","article-title":"Domain-specific language model pretraining for biomedical natural language processing","volume":"3","author":"Gu","year":"2022","journal-title":"ACM Transactions on Computing for Healthcare"},{"key":"10.1016\/j.eswa.2026.131725_bib0037","unstructured":"Gu, Y., Zhang, S., Usuyama, N., Woldesenbet, Y., Wong, C., Sanapathi, P., Wei, M., Valluri, N., Strandberg, E., Naumann, T., & Poon, H. (2023). Distilling large language models for biomedical knowledge extraction: A case study on adverse drug events. 10.48550\/ARXIV.2307.06439."},{"key":"10.1016\/j.eswa.2026.131725_bib0038","unstructured":"Gururajan, A. K., Lopez-Cuena, E., Bayarri-Planas, J., Tormos, A., Hinjos, D., Bernabeu-Perez, P., Arias-Duart, A., Martin-Torres, P. A., Urcelay-Ganzabal, L., Gonzalez-Mallo, M., \u00c1lvarez-Napagao, S., Parra, E. A., Cort\u00e9s, U., & Garcia-Gasulla, D. (2024). Aloe: A family of fine-tuned open healthcare LLMs. 10.48550\/ARXIV.2405.01886."},{"issue":"14","key":"10.1016\/j.eswa.2026.131725_bib0039","doi-asserted-by":"crossref","first-page":"i37","DOI":"10.1093\/bioinformatics\/btx228","article-title":"Deep learning with word embeddings improves biomedical named entity recognition","volume":"33","author":"Habibi","year":"2017","journal-title":"Bioinformatics"},{"issue":"1","key":"10.1016\/j.eswa.2026.131725_bib0040","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1186\/s12911-020-1026-2","article-title":"Customization scenarios for de-identification of clinical notes","volume":"20","author":"Hartman","year":"2020","journal-title":"BMC Medical Informatics and Decision Making"},{"key":"10.1016\/j.eswa.2026.131725_bib0041","series-title":"The eleventh international conference on learning representations, ICLR 2023, Kigali, Rwanda, May 1\u20135, 2023","article-title":"DeBERTav3: Improving deBERTa using ELECTRA-style pre-training with gradient-disentangled embedding sharing","author":"He","year":"2023"},{"key":"10.1016\/j.eswa.2026.131725_bib0042","unstructured":"Hinton, G. E., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. http:\/\/arxiv.org\/abs\/1503.02531."},{"key":"10.1016\/j.eswa.2026.131725_bib0043","unstructured":"Huang, K., Altosaar, J., & Ranganath, R. (2019). ClinicalBERT: Modeling clinical notes and predicting hospital readmission. http:\/\/arxiv.org\/abs\/1904.05342."},{"key":"10.1016\/j.eswa.2026.131725_bib0044","unstructured":"Huang, Z., Xu, W., & Yu, K. (2015). Bidirectional LSTM-CRF models for sequence tagging. http:\/\/arxiv.org\/abs\/1508.01991."},{"key":"10.1016\/j.eswa.2026.131725_bib0045","doi-asserted-by":"crossref","DOI":"10.1007\/s10506-025-09463-9","article-title":"Enhancing legal question answering with data generation and knowledge distillation from large language models","author":"Italiani","year":"2025","journal-title":"Artificial Intelligence and Law"},{"issue":"4","key":"10.1016\/j.eswa.2026.131725_bib0046","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btae163","article-title":"Advancing entity recognition in biomedicine via instruction tuning of large language models","volume":"40","author":"Keloth","year":"2024","journal-title":"Bioinformatics"},{"key":"10.1016\/j.eswa.2026.131725_bib0047","series-title":"Proceedings of the 2024 conference on empirical methods in natural language processing","first-page":"8653","article-title":"Exploring nested named entity recognition with large language models: Methods, challenges, and insights","author":"Kim","year":"2024"},{"key":"10.1016\/j.eswa.2026.131725_bib0048","series-title":"Proceedings of the 2024 conference on empirical methods in natural language processing, EMNLP 2024, Miami, FL, USA, November 12\u201316, 2024","first-page":"21204","article-title":"Generalizing clinical de-identification models by privacy-safe data augmentation using GPT-4","author":"Kim","year":"2024"},{"key":"10.1016\/j.eswa.2026.131725_bib0049","series-title":"Proceedings of the 2016 conference on empirical methods in natural language processing, EMNLP 2016, Austin, Texas, USA, November 1\u20134, 2016","first-page":"1317","article-title":"Sequence-level knowledge distillation","author":"Kim","year":"2016"},{"key":"10.1016\/j.eswa.2026.131725_bib0050","doi-asserted-by":"crossref","unstructured":"Kocaman, V., Haq, H. U., & Talby, D. (2023). Beyond accuracy: Automated de-identification of large real-world clinical text datasets. 10.48550\/ARXIV.2312.08495.","DOI":"10.1016\/j.jval.2023.09.2860"},{"issue":"S-1","key":"10.1016\/j.eswa.2026.131725_bib0051","article-title":"The CHEMDNER corpus of chemicals and drugs and its annotation principles","volume":"7","author":"Krallinger","year":"2015","journal-title":"Journal of Cheminformatics"},{"key":"10.1016\/j.eswa.2026.131725_bib0052","series-title":"Findings of the association for computational linguistics, ACL 2024, Bangkok, Thailand and Virtual Meeting, August 11\u201316, 2024","first-page":"5848","article-title":"Biomistral: A collection of open-source pretrained large language models for medical domains","author":"Labrak","year":"2024"},{"issue":"4","key":"10.1016\/j.eswa.2026.131725_bib0053","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","year":"2020","journal-title":"Bioinformatics"},{"key":"10.1016\/j.eswa.2026.131725_bib0054","article-title":"Biocreative V CDR task corpus: A resource for chemical disease relation extraction","volume":"2016","author":"Li","year":"2016","journal-title":"Database: The Journal of Biological Databases and Curation"},{"key":"10.1016\/j.eswa.2026.131725_bib0055","series-title":"Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: Long papers), ACL 2024, Bangkok, Thailand, August 11\u201316, 2024","first-page":"8758","article-title":"Knowcoder: Coding structured knowledge into LLMs for universal information extraction","author":"Li","year":"2024"},{"key":"10.1016\/j.eswa.2026.131725_bib0056","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). Roberta: A robustly optimized BERT pretraining approach. http:\/\/arxiv.org\/abs\/1907.11692."},{"key":"10.1016\/j.eswa.2026.131725_bib0057","unstructured":"Liu, Z., Yu, X., Zhang, L., Wu, Z., Cao, C., Dai, H., Zhao, L., Liu, W., Shen, D., Li, Q., Liu, T., Zhu, D., & Li, X. (2023). Deid-gpt: Zero-shot medical text de-identification by GPT-4. 10.48550\/ARXIV.2303.11032."},{"key":"10.1016\/j.eswa.2026.131725_bib0058","series-title":"Proceedings of the 57th annual meeting of the association for computational linguistics","first-page":"3449","article-title":"Zero-shot entity linking by reading entity descriptions","author":"Logeswaran","year":"2019"},{"issue":"5","key":"10.1016\/j.eswa.2026.131725_bib0059","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbac282","article-title":"BioRED: A rich biomedical relation extraction dataset","volume":"23","author":"Luo","year":"2022","journal-title":"Briefings Bioinformatics"},{"issue":"5","key":"10.1016\/j.eswa.2026.131725_bib0060","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btad310","article-title":"AIONER: All-in-one scheme-based biomedical named entity recognition using deep learning","volume":"39","author":"Luo","year":"2023","journal-title":"Bioinformatics"},{"key":"10.1016\/j.eswa.2026.131725_bib0061","unstructured":"Monajatipoor, M., Yang, J., Stremmel, J., Emami, M., Mohaghegh, F., Rouhsedaghat, M., & Chang, K. (2024). Llms in biomedicine: A study on clinical named entity recognition. 10.48550\/ARXIV.2404.07376."},{"key":"10.1016\/j.eswa.2026.131725_bib0062","series-title":"Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1: Long papers), ACL 2023, Toronto, Canada, July 9\u201314, 2023","first-page":"15991","article-title":"Crosslingual generalization through multitask finetuning","author":"Muennighoff","year":"2023"},{"key":"10.1016\/j.eswa.2026.131725_bib0063","unstructured":"Nayel, H. A., Shashirekha, H. L., Shindo, H., & Matsumoto, Y. (2019). Improving multi-word entity recognition for biomedical texts. http:\/\/arxiv.org\/abs\/1908.05691."},{"key":"10.1016\/j.eswa.2026.131725_bib0064","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1186\/1472-6947-8-32","article-title":"Automated de-identification of free-text medical records","volume":"8","author":"Neamatullah","year":"2008","journal-title":"BMC Medical Informatics and Decision Making"},{"key":"10.1016\/j.eswa.2026.131725_bib0065","series-title":"SIGIR \u201921: The 44th international ACM SIGIR conference on research and development in information retrieval, Virtual Event, Canada, July 11\u201315, 2021","first-page":"1642","article-title":"DOZEN: Cross-domain zero shot named entity recognition with knowledge graph","author":"Nguyen","year":"2021"},{"key":"10.1016\/j.eswa.2026.131725_bib0066","series-title":"Proceedings of the 2019 conference of the north American chapter of the association for computational linguistics: Human language technologies, volume 1 (long and short papers)","first-page":"807","article-title":"Description-based zero-shot fine-grained entity typing","author":"Obeidat","year":"2019"},{"key":"10.1016\/j.eswa.2026.131725_bib0067","series-title":"Proceedings of the 18th bioNLP workshop and shared task","first-page":"58","article-title":"Transfer learning in biomedical natural language processing: An evaluation of BERT and ELMo on ten benchmarking datasets","author":"Peng","year":"2019"},{"key":"10.1016\/j.eswa.2026.131725_bib0068","series-title":"Findings of the association for computational linguistics: ACL 2024","first-page":"9441","article-title":"Description boosting for zero-shot entity and relation classification","author":"Picco","year":"2024"},{"key":"10.1016\/j.eswa.2026.131725_bib0069","series-title":"Proceedings of the 61st annual meeting of the association for computational linguistics: System demonstrations, ACL 2023, Toronto, Canada, July 10\u201312, 2023","first-page":"357","article-title":"Zshot: An open-source framework for zero-shot named entity recognition and relation extraction","author":"Picco","year":"2023"},{"issue":"6","key":"10.1016\/j.eswa.2026.131725_bib0070","doi-asserted-by":"crossref","first-page":"868","DOI":"10.1093\/bioinformatics\/btt580","article-title":"Anatomical entity mention recognition at literature scale","volume":"30","author":"Pyysalo","year":"2014","journal-title":"Bioinformatics"},{"key":"10.1016\/j.eswa.2026.131725_bib0071","series-title":"The twelfth international conference on learning representations, ICLR 2024, Vienna, Austria, May 7\u201311, 2024","article-title":"GoLLIE: Annotation guidelines improve zero-shot information-extraction","author":"Sainz","year":"2024"},{"issue":"5","key":"10.1016\/j.eswa.2026.131725_bib0072","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1136\/jamia.2009.001560","article-title":"Mayo clinical text analysis and knowledge extraction system (cTAKES): architecture, component evaluation and applications","volume":"17","author":"Savova","year":"2010","journal-title":"Journal of the American Medical Informatics Association"},{"key":"10.1016\/j.eswa.2026.131725_bib0073","series-title":"Proceedings of the 63rd annual meeting of the association for computational linguistics (volume 6: Industry track)","first-page":"510","article-title":"RedactOR: An LLM-powered framework for automatic clinical data de-identification","author":"Singh","year":"2025"},{"issue":"Suppl 2","key":"10.1016\/j.eswa.2026.131725_bib0074","article-title":"Overview of biocreative II gene mention recognition","volume":"9 Suppl 2","author":"Smith","year":"2008","journal-title":"Genome Biology"},{"key":"10.1016\/j.eswa.2026.131725_bib0075","unstructured":"Sounack, T., Davis, J., Durieux, B. N., Chaffin, A., Pollard, T. J., Lehman, E., Johnson, A. E. W., McDermott, M. B. A., Naumann, T., & Lindvall, C. (2025). Bioclinical modernbert: A state-of-the-art long-context encoder for biomedical and clinical NLP. 10.48550\/ARXIV.2506.10896."},{"key":"10.1016\/j.eswa.2026.131725_bib0076","doi-asserted-by":"crossref","first-page":"S20","DOI":"10.1016\/j.jbi.2015.07.020","article-title":"Annotating longitudinal clinical narratives for de-identification: The 2014 i2b2\/UTHealth corpus","volume":"58","author":"Stubbs","year":"2015","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"issue":"2","key":"10.1016\/j.eswa.2026.131725_bib0077","doi-asserted-by":"crossref","first-page":"13:1","DOI":"10.1145\/3293318","article-title":"A survey of zero-shot learning: settings, methods, and applications","volume":"10","author":"Wang","year":"2019","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"issue":"10","key":"10.1016\/j.eswa.2026.131725_bib0078","doi-asserted-by":"crossref","first-page":"1745","DOI":"10.1093\/bioinformatics\/bty869","article-title":"Cross-type biomedical named entity recognition with deep multi-task learning","volume":"35","author":"Wang","year":"2019","journal-title":"Bioinformatics"},{"key":"10.1016\/j.eswa.2026.131725_bib0079","unstructured":"Wang, X., Zhou, W., Zu, C., Xia, H., Chen, T., Zhang, Y., Zheng, R., Ye, J., Zhang, Q., Gui, T., Kang, J., Yang, J., Li, S., & Du, C. (2023). InstructUIE: Multi-task instruction tuning for unified information extraction. 10.48550\/ARXIV.2304.08085."},{"key":"10.1016\/j.eswa.2026.131725_bib0080","doi-asserted-by":"crossref","DOI":"10.1093\/database\/bas041","article-title":"Accelerating literature curation with text-mining tools: a case study of using pubtator to curate genes in pubmed abstracts","volume":"2012","author":"Wei","year":"2012","journal-title":"Database: The Journal of Biological Databases and Curation"},{"key":"10.1016\/j.eswa.2026.131725_bib0081","series-title":"Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP)","first-page":"6397","article-title":"Scalable zero-shot entity linking with dense entity retrieval","author":"Wu","year":"2020"},{"issue":"9","key":"10.1016\/j.eswa.2026.131725_bib0082","doi-asserted-by":"crossref","first-page":"2251","DOI":"10.1109\/TPAMI.2018.2857768","article-title":"Zero-shot learning - A comprehensive evaluation of the good, the bad and the ugly","volume":"41","author":"Xian","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.131725_bib0083","unstructured":"Xu, Z., Jiang, F., Niu, L., Deng, Y., Poovendran, R., Choi, Y., & Lin, B. Y. (2024). Magpie: Alignment data synthesis from scratch by prompting aligned LLMs with nothing. 10.48550\/ARXIV.2406.08464."},{"key":"10.1016\/j.eswa.2026.131725_bib0084","unstructured":"Yang, A., Li, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Gao, C., Huang, C., Lv, C., Zheng, C., Liu, D., Zhou, F., Huang, F., Hu, F., Ge, H., Wei, H., Lin, H., Tang, J., Yang, J., Tu, J., Zhang, J., Yang, J., Yang, J., Zhou, J., Zhou, J., Lin, J., Dang, K., Bao, K., Yang, K., Yu, L., Deng, L., Li, M., Xue, M., Li, M., Zhang, P., Wang, P., Zhu, Q., Men, R., Gao, R., Liu, S., Luo, S., Li, T., Tang, T., Yin, W., Ren, X., Wang, X., Zhang, X., Ren, X., Fan, Y., Su, Y., Zhang, Y., Zhang, Y., Wan, Y., Liu, Y., Wang, Z., Cui, Z., Zhang, Z., Zhou, Z., & Qiu, Z. (2025a). Qwen3 technical report. 10.48550\/ARXIV.2505.09388."},{"key":"10.1016\/j.eswa.2026.131725_bib0085","unstructured":"Yang, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Li, C., Liu, D., Huang, F., Wei, H., Lin, H., Yang, J., Tu, J., Zhang, J., Yang, J., Yang, J., Zhou, J., Lin, J., Dang, K., Lu, K., Bao, K., Yang, K., Yu, L., Li, M., Xue, M., Zhang, P., Zhu, Q., Men, R., Lin, R., Li, T., Xia, T., Ren, X., Ren, X., Fan, Y., Su, Y., Zhang, Y., Wan, Y., Liu, Y., Cui, Z., Zhang, Z., & Qiu, Z. (2024a). Qwen2.5 technical report. 10.48550\/ARXIV.2412.15115."},{"key":"10.1016\/j.eswa.2026.131725_bib0086","unstructured":"Yang, Y., Zhao, W., Huang, C., Ye, J., Wang, X., Zheng, H., Nan, Y., Wang, Y., Xu, X., Huang, K., Zhang, Y., Gui, T., Zhang, Q., & Huang, X. (2024b). Beyond boundaries: Learning a universal entity taxonomy across datasets and languages for open named entity recognition. 10.48550\/ARXIV.2406.11192."},{"key":"10.1016\/j.eswa.2026.131725_bib0087","series-title":"Proceedings of the 31st international conference on computational linguistics, COLING 2025, Abu Dhabi, UAE, January 19\u201324, 2025","first-page":"10902","article-title":"Beyond boundaries: Learning a universal entity taxonomy across datasets and languages for open named entity recognition","author":"Yang","year":"2025"},{"key":"10.1016\/j.eswa.2026.131725_bib0088","doi-asserted-by":"crossref","first-page":"110385","DOI":"10.1109\/ACCESS.2024.3439680","article-title":"Zero and few short learning using large language models for de-identification of medical records","volume":"12","author":"Yashwanth","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2026.131725_bib0089","unstructured":"Yazdani, A., Stepanov, I., & Teodoro, D. (2025). Gliner-biomed: A suite of efficient models for open biomedical named entity recognition. 10.48550\/ARXIV.2504.00676."},{"issue":"3","key":"10.1016\/j.eswa.2026.131725_bib0090","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1080\/08839514.2020.1718343","article-title":"A review of automatic end-to-end de-identification: is high accuracy the only metric?","volume":"34","author":"Yogarajan","year":"2020","journal-title":"Applied Artifical Intelligence"},{"issue":"10","key":"10.1016\/j.eswa.2026.131725_bib0091","first-page":"55","article-title":"Collabonet: Collaboration of deep neural networks for biomedical named entity recognition","volume":"20-S","author":"Yoon","year":"2019","journal-title":"BMC Bioinformatics"},{"key":"10.1016\/j.eswa.2026.131725_bib0092","first-page":"19458","article-title":"SeqGPT: An out-of-the-box large language model for open domain sequence understanding","author":"Yu","year":"2024"},{"key":"10.1016\/j.eswa.2026.131725_bib0093","doi-asserted-by":"crossref","unstructured":"Zamai, A., Zugarini, A., Rigutini, L., Ernandes, M., & Maggini, M. (2024). Show less, instruct more: Enriching prompts with definitions and guidelines for zero-shot NER. 10.48550\/ARXIV.2407.01272.","DOI":"10.1109\/IJCNN64981.2025.11228663"},{"key":"10.1016\/j.eswa.2026.131725_bib0094","series-title":"Proceedings of the 2024 conference of the north american chapter of the association for computational linguistics: Human language technologies (volume 1: Long papers)","first-page":"5364","article-title":"GLINER: Generalist model for named entity recognition using bidirectional transformer","author":"Zaratiana","year":"2024"},{"key":"10.1016\/j.eswa.2026.131725_bib0095","unstructured":"Zhang, Y., Zhang, Y., Qi, P., Manning, C. D., & Langlotz, C. P. (2020). Biomedical and clinical english model packages in the stanza python NLP library. https:\/\/arxiv.org\/abs\/2007.14640."},{"key":"10.1016\/j.eswa.2026.131725_bib0096","series-title":"The twelfth international conference on learning representations, ICLR 2024, Vienna, Austria, May 7\u201311, 2024","article-title":"UniversalNER: Targeted distillation from large language models for open named entity recognition","author":"Zhou","year":"2024"},{"key":"10.1016\/j.eswa.2026.131725_bib0097","doi-asserted-by":"crossref","unstructured":"Zhu, J., Shi, A., Li, Z., Bai, L., Jin, X., Guo, J., & Cheng, X. (2025). Towards robust universal information extraction: Benchmark, evaluation, and solution. 10.48550\/ARXIV.2503.03201.","DOI":"10.18653\/v1\/2025.acl-long.1360"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095741742600638X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095741742600638X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T01:07:10Z","timestamp":1777597630000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S095741742600638X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":97,"alternative-id":["S095741742600638X"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131725","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"OpenBioNER-v2: A suite of lightweight models for zero-shot medical named entity recognition via type descriptions","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131725","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"131725"}}