{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T11:49:17Z","timestamp":1780400957176,"version":"3.54.1"},"reference-count":29,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2020,9,25]],"date-time":"2020-09-25T00:00:00Z","timestamp":1600992000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61572139"],"award-info":[{"award-number":["61572139"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872094"],"award-info":[{"award-number":["61872094"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2017SHZDZX01"],"award-info":[{"award-number":["2017SHZDZX01"]}]},{"name":"Information Technology Facility"},{"name":"CAS-MPG Partner Institute for Computational Biology"},{"name":"Shanghai Institute for Biological Sciences"},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"111 Project","doi-asserted-by":"publisher","award":["B18015"],"award-info":[{"award-number":["B18015"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Science & Technology","award":["16JC1420402"],"award-info":[{"award-number":["16JC1420402"]}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2018SHZDZX01"],"award-info":[{"award-number":["2018SHZDZX01"]}]},{"name":"ZJLab"},{"DOI":"10.13039\/501100001695","name":"JST","doi-asserted-by":"publisher","award":["JPMJAC1503"],"award-info":[{"award-number":["JPMJAC1503"]}],"id":[{"id":"10.13039\/501100001695","id-type":"DOI","asserted-by":"publisher"}]},{"name":"MEXT Kakenhi","award":["19H04169"],"award-info":[{"award-number":["19H04169"]}]},{"name":"AIPSE by Academy of Finland"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>With the rapid increase of biomedical articles, large-scale automatic Medical Subject Headings (MeSH) indexing has become increasingly important. FullMeSH, the only method for large-scale MeSH indexing with full text, suffers from three major drawbacks: FullMeSH (i) uses Learning To Rank, which is time-consuming, (ii) can capture some pre-defined sections only in full text and (iii) ignores the whole MEDLINE database.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We propose a computationally lighter, full text and deep-learning-based MeSH indexing method, BERTMeSH, which is flexible for section organization in full text. BERTMeSH has two technologies: (i) the state-of-the-art pre-trained deep contextual representation, Bidirectional Encoder Representations from Transformers (BERT), which makes BERTMeSH capture deep semantics of full text. (ii) A transfer learning strategy for using both full text in PubMed Central (PMC) and title and abstract (only and no full text) in MEDLINE, to take advantages of both. In our experiments, BERTMeSH was pre-trained with 3 million MEDLINE citations and trained on \u223c1.5 million full texts in PMC. BERTMeSH outperformed various cutting-edge baselines. For example, for 20\u00a0K test articles of PMC, BERTMeSH achieved a Micro F-measure of 69.2%, which was 6.3% higher than FullMeSH with the difference being statistically significant. Also prediction of 20\u00a0K test articles needed 5\u00a0min by BERTMeSH, while it took more than 10\u00a0h by FullMeSH, proving the computational efficiency of BERTMeSH.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Supplementary information<\/jats:title>\n                    <jats:p>Supplementary data are available at Bioinformatics online<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaa837","type":"journal-article","created":{"date-parts":[[2020,9,11]],"date-time":"2020-09-11T15:12:45Z","timestamp":1599837165000},"page":"684-692","source":"Crossref","is-referenced-by-count":31,"title":["BERTMeSH: deep contextual representation learning for large-scale high-performance MeSH indexing with full text"],"prefix":"10.1093","volume":"37","author":[{"given":"Ronghui","family":"You","sequence":"first","affiliation":[{"name":"School of Computer Science and Shanghai Key Lab of Intelligent Information Processing, Fudan University , Shanghai 200433, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxuan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Shanghai Key Lab of Intelligent Information Processing, Fudan University , Shanghai 200433, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroshi","family":"Mamitsuka","sequence":"additional","affiliation":[{"name":"Bioinformatics Center, Institute for Chemical Research, Kyoto University , Uji, Japan"},{"name":"Department of Computer Science, Aalto University , Espoo, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanfeng","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Shanghai Key Lab of Intelligent Information Processing, Fudan University , Shanghai 200433, China"},{"name":"Institute of Science and Technology for Brain-Inspired Intelligence and Shanghai Institute of Artificial Intelligence Algorithms , Shanghai 200433, China"},{"name":"Ministry of Education, Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence, Fudan University , Shanghai 200433, China"},{"name":"Bio-Med Big Data Center, Key Laboratory of Computational Biology, CAS-MPG Partner Institute for Computational Biology, Shanghai Institute of Nutrition and Health, Shanghai Institutes for Biological Science, Chinese Academy of Sciences , Shanghai 200031, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2020,9,25]]},"reference":[{"key":"2023051704094587500_btaa837-B1","first-page":"268","article-title":"The NLM indexing initiative\u2019s Medical Text Indexer","volume":"107","author":"Aronson","year":"2004","journal-title":"Stud. Health Technol. Inform"},{"key":"2023051704094587500_btaa837-B2","article-title":"Longformer: the long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv Preprint arXiv:2004.05150"},{"key":"2023051704094587500_btaa837-B3","doi-asserted-by":"crossref","first-page":"baz034","DOI":"10.1093\/database\/baz034","article-title":"Building deep learning models for evidence classification from the open access biomedical literature","volume":"2019","author":"Burns","year":"2019","journal-title":"Database"},{"key":"2023051704094587500_btaa837-B4","doi-asserted-by":"crossref","first-page":"1533","DOI":"10.1093\/bioinformatics\/btz756","article-title":"FullMeSH: improving large-scale MeSH indexing with full text","volume":"36","author":"Dai","year":"2020","journal-title":"Bioinformatics"},{"key":"2023051704094587500_btaa837-B5","first-page":"4171","volume-title":"NAACL2019","author":"Devlin","year":"2019"},{"key":"2023051704094587500_btaa837-B6","doi-asserted-by":"crossref","first-page":"1265","DOI":"10.1109\/TSMCB.2012.2227998","article-title":"Efficient semisupervised MEDLINE document clustering with MeSH-semantic and global-content constraints","volume":"43","author":"Gu","year":"2013","journal-title":"IEEE Trans. Cybern"},{"key":"2023051704094587500_btaa837-B7","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"2023051704094587500_btaa837-B8","doi-asserted-by":"crossref","first-page":"2293","DOI":"10.1016\/j.ins.2011.01.029","article-title":"Enhanced clustering of biomedical documents using ensemble non-negative matrix factorization","volume":"181","author":"Huang","year":"2011","journal-title":"Inf. Sci"},{"key":"2023051704094587500_btaa837-B9","first-page":"47","volume-title":"BioASQ2018","author":"Jin","year":"2018"},{"key":"2023051704094587500_btaa837-B10","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv Preprint arXiv:1412.6980"},{"key":"2023051704094587500_btaa837-B11","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","article-title":"BioBERT: pre-trained biomedical language representation model for biomedical text mining","volume":"36","author":"Lee","year":"2020","journal-title":"Bioinformatics"},{"key":"2023051704094587500_btaa837-B12","doi-asserted-by":"crossref","first-page":"1854","DOI":"10.1587\/transinf.E94.D.1854","article-title":"A short introduction to learning to rank","volume":"E94-D","author":"Li","year":"2011","journal-title":"IEICE Trans"},{"key":"2023051704094587500_btaa837-B13","doi-asserted-by":"crossref","first-page":"i339","DOI":"10.1093\/bioinformatics\/btv237","article-title":"MeSHLabeler: improving the accuracy of large-scale MeSH indexing by integrating diverse evidence","volume":"31","author":"Liu","year":"2015","journal-title":"Bioinformatics"},{"key":"2023051704094587500_btaa837-B14","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1007\/s10791-008-9074-8","article-title":"Evaluation of query expansion using MeSH in PubMed","volume":"12","author":"Lu","year":"2009","journal-title":"Inform. Retrieval"},{"key":"2023051704094587500_btaa837-B15","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1186\/s13326-017-0123-3","article-title":"MeSH Now: automatic MeSH indexing at PubMed scale via learning to rank","volume":"8","author":"Mao","year":"2017","journal-title":"J. Biomed. Semant"},{"key":"2023051704094587500_btaa837-B16","first-page":"3111","volume-title":"NIPS2013","author":"Mikolov","year":"2013"},{"key":"2023051704094587500_btaa837-B17","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1186\/s13326-017-0113-5","article-title":"12 years on\u2013is the NLM Medical Text Indexer still useful and relevant?","volume":"8","author":"Mork","year":"2017","journal-title":"J. Biomed. Semant"},{"key":"2023051704094587500_btaa837-B18","volume-title":"BioASQ@ CLEF","author":"Mork","year":"2013"},{"key":"2023051704094587500_btaa837-B19","doi-asserted-by":"crossref","first-page":"i70","DOI":"10.1093\/bioinformatics\/btw294","article-title":"DeepMeSH: deep semantic representation for improving large-scale MeSH indexing","volume":"32","author":"Peng","year":"2016","journal-title":"Bioinformatics"},{"key":"2023051704094587500_btaa837-B20","first-page":"58","volume-title":"Proceedings of the 2019 Workshop on Biomedical Natural Language Processing (BioNLP 2019)","author":"Peng","year":"2019"},{"key":"2023051704094587500_btaa837-B21","first-page":"1532","volume-title":"EMNLP2014","author":"Pennington","year":"2014"},{"key":"2023051704094587500_btaa837-B22","first-page":"2227","volume-title":"NAACL2018","author":"Peters","year":"2018"},{"key":"2023051704094587500_btaa837-B23","doi-asserted-by":"crossref","first-page":"2055","DOI":"10.1016\/j.patcog.2013.01.012","article-title":"Threshold optimisation for multi-label classifiers","volume":"46","author":"Pillai","year":"2013","journal-title":"Pattern Recognit"},{"key":"2023051704094587500_btaa837-B24","doi-asserted-by":"crossref","first-page":"D9","DOI":"10.1093\/nar\/gkz899","article-title":"Database resources of the National Center for Biotechnology Information","volume":"48","author":"Sayers","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2023051704094587500_btaa837-B25","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1007\/s10791-008-9073-9","article-title":"Exploring criteria for successful query expansion in the genomic domain","volume":"12","author":"Stokes","year":"2009","journal-title":"Inform. Retrieval"},{"key":"2023051704094587500_btaa837-B26","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1186\/s12859-015-0564-6","article-title":"An overview of the BIOASQ large-scale biomedical semantic indexing and question answering competition","volume":"16","author":"Tsatsaronis","year":"2015","journal-title":"BMC Bioinformatics"},{"key":"2023051704094587500_btaa837-B27","volume-title":"BioASQ workshop","author":"Tsoumakas","year":"2013"},{"key":"2023051704094587500_btaa837-B28","doi-asserted-by":"crossref","first-page":"3794","DOI":"10.1093\/bioinformatics\/btz142","article-title":"MeSHProbeNet: a self-attentive probe net for MeSH indexing","volume":"35","author":"Xun","year":"2019","journal-title":"Bioinformatics"},{"key":"2023051704094587500_btaa837-B29","doi-asserted-by":"crossref","first-page":"1944","DOI":"10.1093\/bioinformatics\/btp338","article-title":"Enhancing MEDLINE document clustering by incorporating MeSH semantic similarity","volume":"25","author":"Zhu","year":"2009","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaa837\/34500772\/btaa837.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/5\/684\/50356276\/btaa837.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/5\/684\/50356276\/btaa837.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,17]],"date-time":"2023-05-17T00:10:42Z","timestamp":1684282242000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/37\/5\/684\/5911627"}},"subtitle":[],"editor":[{"given":"Wren","family":"Jonathan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2020,9,25]]},"references-count":29,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2021,5,5]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaa837","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.07.04.187674","asserted-by":"object"}]},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,3,1]]},"published":{"date-parts":[[2020,9,25]]}}}