{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:30:54Z","timestamp":1753893054396,"version":"3.41.2"},"reference-count":49,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T00:00:00Z","timestamp":1702944000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Res. Metr. Anal."],"abstract":"<jats:p>Biomedical entity linking task is the task of mapping mention(s) that occur in a particular textual context to a unique concept or<jats:italic>entity<\/jats:italic>in a knowledge base, e.g., the Unified Medical Language System (UMLS). One of the most challenging aspects of the entity linking task is the ambiguity of mentions, i.e., (1) mentions whose surface forms are very similar, but which map to different entities in different contexts, and (2) entities that can be expressed using diverse types of mentions. Recent studies have used BERT-based encoders to encode mentions and entities into distinguishable representations such that their similarity can be measured using distance metrics. However, most real-world biomedical datasets suffer from severe imbalance, i.e., some classes have many instances while others appear only once or are completely absent from the training data. A common way to address this issue is to down-sample the dataset, i.e., to reduce the number instances of the majority classes to make the dataset more balanced. In the context of entity linking, down-sampling reduces the ability of the model to comprehensively learn the representations of mentions in different contexts, which is very important. To tackle this issue, we propose a metric-based learning method that treats a given entity and its mentions as a whole, regardless of the number of mentions in the training set. Specifically, our method uses a triplet loss-based function in conjunction with a clustering technique to learn the representation of mentions and entities. Through evaluations on two challenging biomedical datasets, i.e., MedMentions and BC5CDR, we show that our proposed method is able to address the issue of imbalanced data and to perform competitively with other state-of-the-art models. Moreover, our method significantly reduces computational cost in both training and inference steps. Our source code is publicly available<jats:ext-link>here<\/jats:ext-link>.<\/jats:p>","DOI":"10.3389\/frma.2023.1247094","type":"journal-article","created":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T10:54:21Z","timestamp":1702983261000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A metric learning-based method for biomedical entity linking"],"prefix":"10.3389","volume":"8","author":[{"given":"Ngoc D.","family":"Le","sequence":"first","affiliation":[]},{"given":"Nhung T. H.","family":"Nguyen","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2023,12,19]]},"reference":[{"key":"B1","article-title":"Entity linking and discovery via arborescence-based supervised clustering","author":"Agarwal","year":"2021","journal-title":"CoRR, abs\/2109.01242"},{"key":"B2","article-title":"Entity linking via dual and cross-attention encoders","author":"Agarwal","year":"2020","journal-title":"CoRR, arXiv:2004.03555"},{"key":"B3","first-page":"2598","article-title":"\u201cClustering-based inference for biomedical entity linking,\u201d","volume-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Angell","year":"2021"},{"key":"B4","doi-asserted-by":"crossref","DOI":"10.2172\/1453938","volume-title":"A Survey of Techniques for Fixed Radius Near Neighbor Searching","author":"Bentley","year":"1975"},{"key":"B5","article-title":"Fast and effective biomedical entity linking using a dual encoder","volume-title":"Proceedings of the 12th International Workshop on Health Text Mining and Information Analysis","author":"Bhowmik","year":"2021"},{"key":"B6","doi-asserted-by":"publisher","first-page":"D267","DOI":"10.1093\/nar\/gkh061","article-title":"The Unified Medical Language System (UMLS): integrating biomedical terminology","volume":"32","author":"Bodenreider","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"B7","doi-asserted-by":"crossref","first-page":"730","DOI":"10.1007\/978-3-319-46454-1_44","article-title":"\u201cImproving semantic embedding consistency by metric learning for zero-shot classification,\u201d","volume-title":"Computer Vision-ECCV 2016: 14th European Conference","author":"Bucher","year":"2016"},{"key":"B8","article-title":"Autoregressive entity retrieval","author":"Cao","year":"2020","journal-title":"CoRR, arXiv:2010.00904"},{"key":"B9","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2013.299","article-title":"\u201cSimilarity metric learning for face recognition,\u201d","volume-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","author":"Cao","year":"2013"},{"key":"B10","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.145","article-title":"\u201cBeyond triplet loss: a deep quadruplet network for person re-identification,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Chen","year":"2017"},{"key":"B11","first-page":"539","article-title":"\u201cLearning a similarity metric discriminatively, with application to face verification,\u201d","volume-title":"2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), Vol. 1","author":"Chopra","year":"2005"},{"key":"B12","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1145\/1273496.1273523","article-title":"\u201cInformation-theoretic metric learning,\u201d","volume-title":"Proceedings of the 24th International Conference on Machine Learning, ICML '07","author":"Davis","year":"2007"},{"key":"B13","first-page":"4171","article-title":"\u201cBERT: pre-training of deep bidirectional transformers for language understanding,\u201d","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol. 1","author":"Devlin","year":"2019"},{"key":"B14","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01261-8_28","article-title":"\u201cTriplet loss in siamese network for object tracking,\u201d","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Dong","year":"2018"},{"key":"B15","first-page":"1383","article-title":"\u201cThe hitchhiker's guide to testing statistical significance in natural language processing,\u201d","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Vol. 1","author":"Dror","year":"2018"},{"key":"B16","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.neuroimage.2013.10.005","article-title":"Alzheimer's disease neuroimaging initiative. Analysis of sampling techniques for imbalanced data: an n = 648 ADNI study","volume":"87","author":"Dubey","year":"2014","journal-title":"Neuroimage"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1811.07514","article-title":"NSEEN: neural semantic embedding for entity normalization","author":"Fakhraei","year":"2018","journal-title":"CoRR, arXiv:1811.07514"},{"key":"B18","doi-asserted-by":"publisher","first-page":"2940","DOI":"10.1109\/TNNLS.2020.3047335","article-title":"Dynamically weighted balanced loss: Class imbalanced learning and confidence calibration of deep neural networks","volume":"33","author":"Fernando","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B19","doi-asserted-by":"crossref","first-page":"528","DOI":"10.18653\/v1\/K19-1049","article-title":"\u201cLearning dense representations for entity retrieval,\u201d","volume-title":"Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)","author":"Gillick","year":"2019"},{"key":"B20","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1007\/978-3-319-24261-3_7","article-title":"\u201cDeep metric learning using triplet network,\u201d","volume-title":"Similarity-Based Pattern Recognition","author":"Hoffer","year":"2015"},{"key":"B21","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1016\/j.ins.2022.08.074","article-title":"A neural network learning algorithm for highly imbalanced data classification","volume":"612","author":"Huang","year":"2022","journal-title":"Inform. Sci"},{"key":"B22","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","article-title":"Billion-scale similarity search with GPUs","volume":"7","author":"Johnson","year":"2019","journal-title":"IEEE Trans. Big Data"},{"key":"B23","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1186\/s40537-019-0192-5","article-title":"Survey on deep learning with class imbalance","volume":"6","author":"Johnson","year":"2019","journal-title":"J. Big Data"},{"key":"B24","doi-asserted-by":"publisher","first-page":"73729","DOI":"10.1109\/ACCESS.2019.2920708","article-title":"A neural named entity recognition and multi-type normalization tool for biomedical text mining","volume":"7","author":"Kim","year":"2019","journal-title":"IEEE Access"},{"key":"B25","article-title":"\u201cAdam: a method for stochastic optimization,\u201d","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kingma","year":"2015"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1704.01285","article-title":"Smart mining for deep metric learning","author":"Kumar","year":"2017","journal-title":"CoRR, arXiv:1704.01285"},{"key":"B27","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1186\/s12859-017-1609-9","article-title":"A neural joint model for entity and relation extraction from biomedical text","volume":"18","author":"Li","year":"2017","journal-title":"BMC Bioinformatics"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1093\/database\/baw068","article-title":"BioCreative V CDR task corpus: a resource for chemical disease relation extraction","author":"Li","year":"2016","journal-title":"Database"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.334","article-title":"\u201cSelfalignment pre-training for biomedical entity representations,\u201d","author":"Liu","year":"2020","journal-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies"},{"key":"B30","doi-asserted-by":"crossref","first-page":"55","DOI":"10.3115\/v1\/P14-5010","article-title":"\u201cThe Stanford CoreNLP natural language processing toolkit,\u201d","volume-title":"Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations","author":"Manning","year":"2014"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1902.09476","article-title":"Medmentions: a large biomedical corpus annotated with UMLS concepts","author":"Mohan","year":"2019","journal-title":"CoRR, arXiv:1902.09476"},{"key":"B32","article-title":"Pytorch: an imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"CoRR, abs\/1912.01703"},{"key":"B33","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1109\/MIPR.2018.00027","article-title":"\u201cDynamic sampling in convolutional neural networks for imbalanced data classification,\u201d","volume-title":"2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)","author":"Pouyanfar","year":"2018"},{"key":"B34","doi-asserted-by":"crossref","first-page":"3982","DOI":"10.18653\/v1\/D19-1410","article-title":"\u201cSentence-Bert: sentence embeddings using Siamese bert-networks,\u201d","volume-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)","author":"Reimers","year":"2019"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682","article-title":"Facenet: a unified embedding for face recognition and clustering","author":"Schroff","year":"2015","journal-title":"CoRR, abs\/1503.03832"},{"key":"B36","article-title":"\u201cImproved deep metric learning with multi-class n-pair loss objective,\u201d","volume-title":"Advances in Neural Information Processing Systems, Vol. 29","author":"Sohn","year":"2016"},{"key":"B37","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1186\/1471-2105-9-402","article-title":"Abbreviation definition identification based on automatic precision estimates","volume":"9","author":"Sohn","year":"2008","journal-title":"BMC Bioinformatics"},{"key":"B38","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1007\/BF02288916","article-title":"Multidimensional scaling: I. theory and method","volume":"17","author":"Torgerson","year":"1952","journal-title":"Psychometrika"},{"key":"B39","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"CoRR, abs\/1706.03762"},{"key":"B40","article-title":"\u201cA deep architecture for semantic matching with multiple positional sentence representations,\u201d","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 30","author":"Wan","year":"2015"},{"key":"B41","doi-asserted-by":"publisher","first-page":"176","DOI":"10.3390\/info14030176","article-title":"Ontology learning applications of knowledge base construction for microelectronic systems information","volume":"14","author":"Wawrzik","year":"2023","journal-title":"Information"},{"key":"B42","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1007\/s11263-018-01142-4","article-title":"A comprehensive study on center loss for deep face recognition","volume":"127","author":"Wen","year":"2019","journal-title":"Int. J. Comput. Vis"},{"key":"B43","doi-asserted-by":"crossref","first-page":"143","DOI":"10.18653\/v1\/D19-6116","article-title":"\u201cMetric learning for dynamic text classification,\u201d","volume-title":"Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)","author":"Wohlwend","year":"2019"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/3526539","article-title":"An improved oversampling algorithm based on the samples' selection strategy for classifying imbalanced data","author":"Xie","year":"2019","journal-title":"Math. Probl. Eng"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1093\/database\/baw036","article-title":"CD-REST: a system for extracting chemical-induced disease relation in literature","author":"Xu","year":"2016","journal-title":"Database"},{"key":"B46","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1007\/978-3-030-58568-6_8","article-title":"\u201cHard negative examples are hard, but useful,\u201d","volume-title":"Computer Vision-ECCV 2020","author":"Xuan","year":"2020"},{"key":"B47","first-page":"4038","article-title":"\u201cGenerative biomedical entity linking via knowledge base-guided pre-training and synonyms-aware fine-tuning,\u201d","volume-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Yuan","year":"2022"},{"key":"B48","doi-asserted-by":"crossref","first-page":"868","DOI":"10.18653\/v1\/2022.findings-emnlp.61","article-title":"\u201cKnowledge-rich self-supervision for biomedical entity linking,\u201d","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2022","author":"Zhang","year":"2022"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.101993","article-title":"Deep metric learning-based image retrieval system for chest radiograph and its clinical applications in COVID-19","author":"Zhong","year":"2021","journal-title":"Med. Image Anal"}],"container-title":["Frontiers in Research Metrics and Analytics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frma.2023.1247094\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T09:29:10Z","timestamp":1730885350000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frma.2023.1247094\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,19]]},"references-count":49,"alternative-id":["10.3389\/frma.2023.1247094"],"URL":"https:\/\/doi.org\/10.3389\/frma.2023.1247094","relation":{},"ISSN":["2504-0537"],"issn-type":[{"type":"electronic","value":"2504-0537"}],"subject":[],"published":{"date-parts":[[2023,12,19]]},"article-number":"1247094"}}