{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T19:30:13Z","timestamp":1790537413254,"version":"4.1.0"},"reference-count":91,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2021,2,11]],"date-time":"2021-02-11T00:00:00Z","timestamp":1613001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,3,22]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Biomedical scientific literature is growing at a very rapid pace, which makes increasingly difficult for human experts to spot the most relevant results hidden in the papers. Automatized information extraction tools based on text mining techniques are therefore needed to assist them in this task. In the last few years, deep neural networks-based techniques have significantly contributed to advance the state-of-the-art in this research area. Although the contribution to this progress made by supervised methods is relatively well-known, this is less so for other kinds of learning, namely unsupervised and self-supervised learning. Unsupervised learning is a kind of learning that does not require the cost of creating labels, which is very useful in the exploratory stages of a biomedical study where agile techniques are needed to rapidly explore many paths. In particular, clustering techniques applied to biomedical text mining allow to gather large sets of documents into more manageable groups. Deep learning techniques have allowed to produce new clustering-friendly representations of the data. On the other hand, self-supervised learning is a kind of supervised learning where the labels do not have to be manually created by humans, but are automatically derived from relations found in the input texts. In combination with innovative network architectures (e.g. transformer-based architectures), self-supervised techniques have allowed to design increasingly effective vector-based word representations (word embeddings). We show in this survey how word representations obtained in this way have proven to successfully interact with common supervised modules (e.g. classification networks) to whose performance they greatly contribute.<\/jats:p>","DOI":"10.1093\/bib\/bbab016","type":"journal-article","created":{"date-parts":[[2021,1,26]],"date-time":"2021-01-26T12:10:36Z","timestamp":1611663036000},"page":"1592-1603","source":"Crossref","is-referenced-by-count":68,"title":["Unsupervised and self-supervised deep learning approaches for biomedical text mining"],"prefix":"10.1093","volume":"22","author":[{"given":"Mohamed","family":"Nadif","sequence":"first","affiliation":[{"name":"Universit\u00e9 de Paris, CNRS, Centre Borelli, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fran\u00e7ois","family":"Role","sequence":"additional","affiliation":[{"name":"Universit\u00e9 de Paris, CNRS, Centre Borelli, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2021,2,11]]},"reference":[{"key":"2021032314373577900_ref1","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1145\/3340531.3412058","article-title":"Ensemble block co-clustering: a unified framework for text data","volume-title":"Proceedings of the 29th ACM International Conference on Information & Knowledge Management","author":"Affeldt","year":"2020"},{"key":"2021032314373577900_ref2","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2020.107522","article-title":"Spectral clustering via ensemble deep autoencoder learning (SC-EDAE)","volume":"108","author":"Affeldt","year":"2020","journal-title":"Pattern Recogn"},{"key":"2021032314373577900_ref3","doi-asserted-by":"crossref","first-page":"1807","DOI":"10.1145\/2806416.2806639","article-title":"Co-clustering document-term matrices by direct maximization of graph modularity","volume-title":"Proceedings of the 24th ACM International on Conference on Information and Knowledge Management","author":"Ailem","year":"2015"},{"key":"2021032314373577900_ref4","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1016\/j.knosys.2016.07.002","article-title":"Graph modularity maximization as an effective method for co-clustering text data","volume":"109","author":"Ailem","year":"2016","journal-title":"Knowl-Based Syst"},{"key":"2021032314373577900_ref5","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.patcog.2017.06.005","article-title":"Model-based co-clustering for the effective handling of sparse data","volume":"72","author":"Ailem","year":"2017","journal-title":"Pattern Recogn"},{"issue":"7","key":"2021032314373577900_ref6","doi-asserted-by":"crossref","first-page":"1563","DOI":"10.1109\/TKDE.2017.2681669","article-title":"Sparse poisson latent block model for document clustering","volume":"29","author":"Ailem","year":"2017","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"2021032314373577900_ref7","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1016\/j.jbi.2016.02.008","article-title":"Unsupervised text mining for assessing and augmenting GWAS results","volume":"60","author":"Ailem","year":"2016","journal-title":"J Biomed Informatics"},{"key":"2021032314373577900_ref8","doi-asserted-by":"crossref","first-page":"1081","DOI":"10.1145\/3077136.3080727","article-title":"Non-negative matrix factorization meets word embedding","volume-title":"Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Ailem","year":"2017"},{"key":"2021032314373577900_ref9","doi-asserted-by":"crossref","first-page":"2838","DOI":"10.1109\/BigData.2018.8621999","article-title":"Retrofitting word embeddings with the umls metathesaurus for clinical information extraction","volume-title":"IEEE International Conference on Big Data (Big Data)","author":"Alawad","year":"2018"},{"key":"2021032314373577900_ref10","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1137\/1.9781611974348.31","article-title":"Power simultaneous spectral data embedding and clustering","volume-title":"SIAM International Conference on Data Mining, 2016","author":"Allab","year":"2016"},{"issue":"12","key":"2021032314373577900_ref11","doi-asserted-by":"crossref","first-page":"6396","DOI":"10.1109\/TNNLS.2018.2815623","article-title":"Simultaneous spectral data embedding and clustering","volume":"29","author":"Allab","year":"2018","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"1","key":"2021032314373577900_ref12","first-page":"1","article-title":"Variational autoencoder based anomaly detection using reconstruction probability","volume":"2","author":"An","year":"2015","journal-title":"Special Lecture on IE"},{"key":"2021032314373577900_ref13","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1007\/978-3-319-59876-5_42","article-title":"Fast spectral clustering using autoencoders and landmarks","volume-title":"International Conference Image Analysis and Recognition","author":"Banijamali","year":"2017"},{"key":"2021032314373577900_ref14","first-page":"585","article-title":"Laplacian eigenmaps and spectral techniques for embedding and clustering","volume-title":"NIPS","author":"Belkin","year":"2001"},{"issue":"1","key":"2021032314373577900_ref15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000006","article-title":"Learning deep architectures for ai","volume":"2","author":"Bengio","year":"2009","journal-title":"Found Trends Mach Learn"},{"key":"2021032314373577900_ref16","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1162\/tacl_a_00051","article-title":"Enriching word vectors with subword information","volume":"5","author":"Bojanowski","year":"2017","journal-title":"Trans Assoc Comput Linguist"},{"key":"2021032314373577900_ref17","article-title":"Man is to computer programmer as woman is to homemaker? Debiasing word embeddings","author":"Bolukbasi","year":"2016","journal-title":"CoRR"},{"key":"2021032314373577900_ref18","article-title":"Biosentvec: creating sentence embeddings for biomedical texts","author":"Chen","year":"2018","journal-title":"CoRR"},{"key":"2021032314373577900_ref19","doi-asserted-by":"crossref","first-page":"166","DOI":"10.18653\/v1\/W16-2922","article-title":"How to train good word embeddings for biomedical NLP","volume-title":"Proceedings of the 15th Workshop on Biomedical Natural Language Processing","author":"Chiu","year":"2016"},{"key":"2021032314373577900_ref20","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"CoRR"},{"issue":"1\u20132","key":"2021032314373577900_ref21","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1023\/A:1007612920971","article-title":"Concept decompositions for large sparse text data using clustering","volume":"42","author":"Dhillon","year":"2001","journal-title":"Mach Learn"},{"issue":"1","key":"2021032314373577900_ref22","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1109\/TPAMI.2008.277","article-title":"Convex and semi-nonnegative matrix factorizations","volume":"32","author":"Ding","year":"2010","journal-title":"IEEE Trans Patter Anal Mach Intellig"},{"key":"2021032314373577900_ref23","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1145\/1150402.1150420","article-title":"Orthogonal nonnegative matrix t-factorizations for clustering","volume-title":"Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Ding","year":"2006"},{"key":"2021032314373577900_ref24","first-page":"135","article-title":"A survey of dimension reduction methods for high-dimensional data analysis and visualization","volume-title":"OAIS \u2013 Open Access Series in Informatics","author":"Engel","year":"2012"},{"key":"2021032314373577900_ref25","article-title":"Deep k-means: jointly clustering with k-means and learning representations","author":"Fard","year":"2018"},{"key":"2021032314373577900_ref26","article-title":"Retrofitting word vectors to semantic lexicons","author":"Faruqui","year":"2014","journal-title":"CoRR"},{"key":"2021032314373577900_ref27","first-page":"5736","article-title":"Deep clustering via joint convolutional autoencoder embedding and relative entropy minimization","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Ghasedi Dizaji","year":"2017"},{"key":"2021032314373577900_ref28","author":"Gittins","year":"1985"},{"key":"2021032314373577900_ref29","doi-asserted-by":"crossref","DOI":"10.1002\/9781118649480","volume-title":"Co-clustering","author":"Govaert","year":"2013"},{"issue":"3","key":"2021032314373577900_ref30","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1007\/s11634-016-0274-6","article-title":"Mutual information, phi-squared and model-based co-clustering for contingency tables","volume":"12","author":"Govaert","year":"2018","journal-title":"Adv Data Anal Classificat"},{"key":"2021032314373577900_ref31","article-title":"Domain-specific language model pretraining for biomedical natural language processing","author":"Gu","year":"2020"},{"issue":"8","key":"2021032314373577900_ref32","article-title":"Semi-supervised recurrent neural network for adverse drug reaction mention extraction","volume":"19","author":"Gupta","year":"2018","journal-title":"BMC Ioinformat"},{"issue":"14","key":"2021032314373577900_ref33","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":"07 2017","journal-title":"Bioinformatics"},{"key":"2021032314373577900_ref34","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1080\/01621459.1972.10481214","article-title":"Direct clustering of a data matrix","author":"Hartigan","year":"1972","journal-title":"J Am Stat Assoc"},{"issue":"5786","key":"2021032314373577900_ref35","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"Hinton","year":"2006","journal-title":"Science"},{"issue":"8","key":"2021032314373577900_ref36","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":"2021032314373577900_ref37","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015"},{"key":"2021032314373577900_ref38","doi-asserted-by":"crossref","first-page":"633","DOI":"10.3115\/v1\/D14-1070","article-title":"A neural network for factoid question answering over paragraphs","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Iyyer","year":"2014"},{"key":"2021032314373577900_ref39","first-page":"24","article-title":"Deep subspace clustering networks","volume-title":"Advances in Neural Information Processing Systems 30","author":"Ji","year":"2017"},{"key":"2021032314373577900_ref40","article-title":"A study of word embeddings for biomedical question answering","volume-title":"4e \u00e9dition du Symposium sur l\u2019Ing\u00e9nierie de l\u2019Information M\u00e9dicale","author":"Kamath","year":". 2017"},{"key":"2021032314373577900_ref41","first-page":"1","article-title":"Deep learning-based clustering approaches for bioinformatics","author":"Karim","year":"2020","journal-title":"Brief Bioinform"},{"key":"2021032314373577900_ref42","doi-asserted-by":"crossref","DOI":"10.1109\/TCBB.2020.2994649","article-title":"Convolutional embedded networks for population scale clustering and bio-ancestry inferencing","author":"Karim","year":"2020","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"2021032314373577900_ref43","doi-asserted-by":"crossref","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":"2021032314373577900_ref44","first-page":"3294","article-title":"Skip-thought vectors","volume-title":"Advances in Neural Information Processing Systems 28","author":"Kiros","year":"2015"},{"issue":"2","key":"2021032314373577900_ref45","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1002\/aic.690370209","article-title":"Nonlinear principal component analysis using autoassociative neural networks","volume":"37","author":"Kramer","year":"1991","journal-title":"AIChE J"},{"key":"2021032314373577900_ref46","first-page":"1140","article-title":"Co-clustering for binary and categorical data with maximum modularity","volume-title":"IEEE ICDM","author":"Labiod","year":"2011"},{"key":"2021032314373577900_ref47","first-page":"1","article-title":"Efficient regularized spectral data embedding","author":"Labiod","year":"2020","journal-title":"Adv Data Anal Classificat"},{"key":"2021032314373577900_ref48","article-title":"Distributed representations of sentences and documents","volume-title":"Proceedings of the 31st International Conference on International Conference on Machine Learning","author":"Le","year":"2014"},{"key":"2021032314373577900_ref49","first-page":"09","article-title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","author":"Lee","year":"2019","journal-title":"Bioinformatics"},{"key":"2021032314373577900_ref50","first-page":"2177","article-title":"Neural word embedding as implicit matrix factorization","volume-title":"Advances in Neural Information Processing Systems","author":"Levy","year":"2014"},{"key":"2021032314373577900_ref51","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1007\/978-3-319-57529-2_62","article-title":"Denoising autoencoder as an effective dimensionality reduction and clustering of text data","volume-title":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","author":"Leyli-Abadi","year":"2017"},{"key":"2021032314373577900_ref52","doi-asserted-by":"crossref","DOI":"10.1109\/TKDE.2020.3038670","article-title":"A survey on deep learning for named entity recognition","author":"Li","year":"2020","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"2021032314373577900_ref53","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/N15-1092","article-title":"Representation learning using multi-task deep neural networks for semantic classification and information retrieval","author":"Liu","year":"2015"},{"key":"2021032314373577900_ref54","article-title":"A robustly optimized BERT pretraining approach","author":"Liu","year":"2019","journal-title":"CoRR"},{"key":"2021032314373577900_ref55","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013"},{"key":"2021032314373577900_ref56","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","volume-title":"Advances in Neural Information Processing Systems","author":"Mikolov","year":"2013"},{"key":"2021032314373577900_ref57","article-title":"External evaluation of topic models","volume-title":"Australasian Doc. Comp. Symp","author":"Newman","year":"2009"},{"key":"2021032314373577900_ref58","article-title":"An overview of deep semi-supervised learning","author":"Ouali","year":"2020"},{"key":"2021032314373577900_ref59","article-title":"Unsupervised learning of sentence embeddings using compositional n-gram features","author":"Pagliardini","year":"2017","journal-title":"CoRR"},{"key":"2021032314373577900_ref60","first-page":"572","article-title":"Semantic similarity and relatedness between clinical terms: An experimental study","volume":"2010","author":"Pakhomov","year":"2010","journal-title":"AMIA Annu Symp Proc"},{"key":"2021032314373577900_ref61","first-page":"1532","article-title":"Glove: Global vectors for word representation","volume-title":"EMNLP","author":"Pennington","year":"2014"},{"key":"2021032314373577900_ref62","first-page":"39","article-title":"Distributional semantics resources for biomedical text processing","volume-title":"Proceedings of LBM 2013","author":"Pyysalo","year":"2013"},{"key":"2021032314373577900_ref63","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18653\/v1\/2020.bionlp-1.1","article-title":"Quantifying 60 years of gender bias in biomedical research with word embeddings","volume-title":"Proceedings of the 19th SIGBioMed Workshop on Biomedical Language Processing","author":"Rios","year":"2020"},{"issue":"7","key":"2021032314373577900_ref64","first-page":"1","article-title":"Coclust: a python package for co-clustering","volume":"88","author":"Role","year":"2018","journal-title":"J Stat Softw"},{"key":"2021032314373577900_ref65","first-page":"226","article-title":"Handling the impact of low frequency events on co-occurrence based measures of word similarity - a case study of pointwise mutual information","volume-title":"KDIR","author":"Role","year":"2011"},{"issue":"6088","key":"2021032314373577900_ref66","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"2021032314373577900_ref67","article-title":"Effective use of bidirectional language modeling for medical named entity recognition","author":"Sachan","year":"2017","journal-title":"CoRR"},{"key":"2021032314373577900_ref68","first-page":"3992","article-title":"Word co-occurrence regularized non-negative matrix tri-factorization for text data co-clustering","author":"Salah","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"2021032314373577900_ref69","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611974973.28","article-title":"Model-based von mises-fisher co-clustering with a conscience","volume-title":"SIAM International Conference on Data Mining","author":"Salah","year":"2017"},{"issue":"3","key":"2021032314373577900_ref70","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1007\/s11634-018-0323-4","article-title":"Directional co-clustering","volume":"13","author":"Salah","year":"2019","journal-title":"Adv Data Analy Classificat"},{"issue":"4","key":"2021032314373577900_ref71","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1007\/s11222-009-9138-7","article-title":"Dimension reduction for model-based clustering","volume":"20","author":"Scrucca","year":"2010","journal-title":"Statist Comput"},{"key":"2021032314373577900_ref72","first-page":"877","article-title":"Pca-initialized deep neural networks applied to document image analysis","volume-title":"14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017","author":"Seuret","year":"2017"},{"key":"2021032314373577900_ref73","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ICHI.2019.8904533","article-title":"Biomedical semantic embeddings: Using hybrid sentences to construct biomedical word embeddings and its applications","volume-title":"2019 IEEE International Conference on Healthcare Informatics (ICHI)","author":"Shaik","year":"2019"},{"issue":"1","key":"2021032314373577900_ref74","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1353\/pbm.1986.0087","article-title":"Fish oil, raynaud\u2019s syndrome, and undiscovered public knowledge","volume":"30","author":"Swanson","year":"1986","journal-title":"Perspect Biol Med"},{"key":"2021032314373577900_ref75","article-title":"Transfer learning for biomedical named entity recognition with biobert","volume":"2451","author":"Symeonidou","year":"2019","journal-title":"CEUR Workshop Proceedings"},{"key":"2021032314373577900_ref76","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-71246-8_49","article-title":"Deepcluster: A general clustering framework based on deep learning","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"Tian","year":"2017"},{"issue":"1","key":"2021032314373577900_ref77","doi-asserted-by":"crossref","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 Bioinformat"},{"key":"2021032314373577900_ref78","first-page":"66","article-title":"Dimensionality reduction: a comparative","volume":"10","author":"","year":"2009","journal-title":"J Mach Learn Res"},{"key":"2021032314373577900_ref79","first-page":"5998","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems 30","author":"Vaswani","year":"2017"},{"issue":"7","key":"2021032314373577900_ref80","doi-asserted-by":"crossref","first-page":"1661","DOI":"10.1162\/NECO_a_00142","article-title":"A connection between score matching and denoising autoencoders","volume":"23","author":"Vincent","year":"2011","journal-title":"Neural Comput"},{"key":"2021032314373577900_ref81","first-page":"774","article-title":"Nonnegative matrix tri-factorization based high-order co-clustering and its fast implementation","author":"Wang","year":"2011","journal-title":"IEEE International Conference on Data Mining"},{"key":"2021032314373577900_ref82","first-page":"2725","article-title":"Feature selection guided auto-encoder","volume-title":"Thirty-First Conference on Artificial Intelligence (AAAI)","author":"Wang","year":"2017"},{"key":"2021032314373577900_ref83","article-title":"A comparison of word embeddings for the biomedical natural language processing","author":"Wang","year":"2018","journal-title":"CoRR"},{"key":"2021032314373577900_ref84","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","author":"Xie","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"2021032314373577900_ref85","doi-asserted-by":"crossref","first-page":"33432","DOI":"10.1109\/ACCESS.2018.2845840","article-title":"Leveraging biomedical resources in bi-lstm for drug-drug interaction extraction","volume":"6","author":"Xu","year":"2018","journal-title":"IEEE Access"},{"issue":"3","key":"2021032314373577900_ref86","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1007\/s11634-012-0113-3","article-title":"Clustering of functional data in a low-dimensional subspace","volume":"6","author":"Yamamoto","year":"2012","journal-title":"Adv Data Anal Classificat"},{"key":"2021032314373577900_ref87","first-page":"3861","article-title":"Towards k-means-friendly spaces: Simultaneous deep learning and clustering","volume-title":"Proceedings of the 34th International Conference on Machine Learning","author":"Yang","year":"2017"},{"key":"2021032314373577900_ref88","first-page":"3861","article-title":"Towards k-means-friendly spaces: Simultaneous deep learning and clustering","volume-title":"Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research","author":"Yang","year":"2017"},{"issue":"5","key":"2021032314373577900_ref89","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1016\/j.ipm.2009.12.007","article-title":"Orthogonal nonnegative matrix tri-factorization for co-clustering: multiplicative updates on stiefel manifolds","volume":"46","author":"Yoo","year":"2010","journal-title":"Inf Process Manag"},{"issue":"52","key":"2021032314373577900_ref90","article-title":"Biowordvec, improving biomedical word embeddings with subword information and mesh","volume":"6","author":"Zhang","year":"2019","journal-title":"Scientific Data"},{"key":"2021032314373577900_ref91","article-title":"Gender bias in contextualized word embeddings","author":"Zhao","year":"2019","journal-title":"CoRR"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bib\/article-pdf\/22\/2\/1592\/36655075\/bbab016.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/bib\/article-pdf\/22\/2\/1592\/36655075\/bbab016.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,23]],"date-time":"2021-03-23T15:13:19Z","timestamp":1616512399000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/22\/2\/1592\/6132597"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,11]]},"references-count":91,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2021,2,11]]},"published-print":{"date-parts":[[2021,3,22]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbab016","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,3]]},"published":{"date-parts":[[2021,2,11]]}}}