2026-06-17T16:08:30Zhttps://iris.cnr.it/oai/request

oai:iris.cnr.it:20.500.14243/5705012026-03-04T01:27:52Zcom_20.500.14243_22com_20.500.14243_21col_20.500.14243_23ou_ou239

Efficient multi-task learning with instance selection for biomedical NLP Bonfigli A. Bacco L. Pecchia L. Merone M. Dell'Orletta F. Bonfigli, A. Bacco, L. Pecchia, L. Merone, M. Dell'Orletta, F. Biomedical NLP BLUE benchmark Computational efficiency Instance selection Multi-task learning Background: Biomedical natural language processing (NLP) increasingly relies on large language models and extensive datasets, presenting significant computational challenges. Methods: We propose Blue5, a multi-task model based on SciFive that incorporates instance selection (IS) to enable efficient, multi-task learning (MTL) on biomedical data. We adapt the E2SC-IS framework for the biomedical domain, integrating a calibrated SVM classifier to reduce computational costs. Results: Our approach achieves an average data reduction of 26.6% across the several tasks of the BLUE (Biomedical Language Understanding Evaluation) Benchmark, while maintaining performance comparable with state-of-the-art models. The multi-task SVM configuration emerges as the most effective, demonstrating the power of combining IS with MTL for biomedical NLP. As a result of the unified framework, Blue5 effectively selects the most informative instances across tasks, ensuring model generalization while efficiently handling multiple NLP tasks. Conclusion: Our work offers a practical solution to address growing computational demands, enabling more scalable and accessible applications of advanced NLP techniques in biomedical research and healthcare. 2025 info:eu-repo/semantics/article https://hdl.handle.net/20.500.14243/570501 10.1016/j.compbiomed.2025.110050 info:eu-repo/semantics/altIdentifier/scopus/2-s2.0-105001252768 eng volume:190 journal:COMPUTERS IN BIOLOGY AND MEDICINE info:eu-repo/semantics/openAccess license:Creative commons license uri:http://creativecommons.org/licenses/by-nc-nd/4.0/