{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T19:47:02Z","timestamp":1793476022345,"version":"4.5.0"},"reference-count":187,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2018R1A5A1059921"],"award-info":[{"award-number":["NRF-2018R1A5A1059921"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"SK Telecom"},{"name":"Google AI Focused Research"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2021,4,1]]},"DOI":"10.1109\/tkde.2019.2946162","type":"journal-article","created":{"date-parts":[[2019,10,8]],"date-time":"2019-10-08T16:06:27Z","timestamp":1570550787000},"page":"1328-1347","source":"Crossref","is-referenced-by-count":718,"title":["A Survey on Data Collection for Machine Learning: A Big Data - AI Integration Perspective"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8110-5397","authenticated-orcid":false,"given":"Yuji","family":"Roh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0370-2732","authenticated-orcid":false,"given":"Geon","family":"Heo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6419-931X","authenticated-orcid":false,"given":"Steven Euijong","family":"Whang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref171","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2015","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref174","article-title":"Tensorflow hub","year":"0"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0043-6"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-5004"},{"key":"ref175","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1109\/TPAMI.2006.79","article-title":"One-shot learning of object categories","volume":"28","author":"li","year":"2006","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-017-0089-0"},{"key":"ref177","first-page":"3320","article-title":"How transferable are features in deep neural networks?","author":"yosinski","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.168"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.239"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.14778\/3157794.3157804"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2882952"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213912"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.14778\/1938545.1938547"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213848"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687750"},{"key":"ref37","first-page":"993","article-title":"Latent dirichlet allocation","volume":"3","author":"blei","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref35","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc 26th Int Conf Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-8265-9_1154"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2292894"},{"key":"ref180","article-title":"Tensorflow data validation","year":"0"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"ref183","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref182","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186133"},{"key":"ref186","first-page":"1527","article-title":"Anchors: High-precision model-agnostic explanations","author":"ribeiro","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2723725"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-011-0223-0"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098021"},{"key":"ref29","first-page":"15","article-title":"Data services leveraging bing's data assets","volume":"39","author":"chakrabarti","year":"2016","journal-title":"IEEE Data Eng Bull"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2903730"},{"key":"ref22","article-title":"The data civilizer system","author":"deng","year":"2017","journal-title":"Proc Biennial Conf Innovative Data Syst Res"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3058740"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.14778\/1453856.1453916"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3183746"},{"key":"ref101","first-page":"912","article-title":"Semi-supervised learning using gaussian fields and harmonic functions","author":"zhu","year":"2003","journal-title":"Proc 20th Int Conf Int Conf Mach Learn"},{"key":"ref26","article-title":"Google dataset search","year":"0"},{"key":"ref100","first-page":"519","article-title":"Large scale distributed semi-supervised learning using streaming approximation","author":"ravi","year":"2016","journal-title":"Proc Int Conf Artif Intell Statistics"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.14778\/3229863.3240492"},{"key":"ref50","first-page":"211","article-title":"Crowdsourced databases: Query processing with people","author":"marcus","year":"2011","journal-title":"Proc Biennial Conf Innovative Data Syst Res"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2012.122"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1145\/2939502.2939515"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwx106"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.3115\/1690219.1690287"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3056442"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1145\/3274423"},{"key":"ref152","article-title":"The role of massively multi-task and weak supervision in software 2.0","author":"ratner","year":"2019","journal-title":"Proc Biennial Conf Innovative Data Syst Res"},{"key":"ref151","article-title":"Weak supervision: The new programming paradigm for machine learning","year":"0"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7637-6"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-12637-1_27"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1007\/s10619-014-7163-9"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.14778\/3231751.3231757"},{"key":"ref58","first-page":"286","article-title":"Generating multi-label discrete patient records using generative adversarial networks","author":"choi","year":"2017","journal-title":"Proc 2nd Mach Learn Healthcare Conf"},{"key":"ref57","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2588576"},{"key":"ref55","article-title":"Data curation at scale: The data tamer system","author":"stonebraker","year":"2013","journal-title":"Proc Biennial Conf Innovative Data Syst Res"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s10619-014-7163-9"},{"key":"ref53","first-page":"577","article-title":"Crowdfill: Collecting structured data from the crowd","author":"park","year":"2014","journal-title":"Proc ACM SIGMOD Int Conf Manage Data"},{"key":"ref52","first-page":"673","article-title":"Crowdsourced enumeration queries","author":"franklin","year":"2013","journal-title":"Proc IEEE Int Conf Data Eng"},{"key":"ref40","first-page":"3","article-title":"Data integration: The current status and the way forward","volume":"41","author":"stonebraker","year":"2018","journal-title":"IEEE Data Eng Bull"},{"key":"ref167","first-page":"2691","article-title":"Learning from massive noisy labeled data for image classification","author":"xiao","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1145\/3329486.3329493"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1145\/1993498.1993536"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1145\/2254556.2254659"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1979444"},{"key":"ref162","first-page":"381","article-title":"Potter's wheel: An interactive data cleaning system","author":"raman","year":"2001","journal-title":"Proc 27th Int Conf Very Large Data Bases"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.14778\/3297753.3297758"},{"key":"ref160","article-title":"Boostclean: Automated error detection and repair for machine learning","volume":"abs 1711 1299","author":"krishnan","year":"2017","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3299887.3299891"},{"key":"ref3","first-page":"273","article-title":"Learning the structure of generative models without labeled data","author":"bach","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref6","article-title":"Google cloud automl","year":"0"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3054782"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994514"},{"key":"ref8","article-title":"Amazon sagemaker","year":"0"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1989323.1989331"},{"key":"ref7","article-title":"Microsoft custom vision","year":"0"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2014.07.007"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137631"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.14778\/2824032.2824100"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2384616.2384663"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1866029.1866040"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.14778\/2367502.2367555"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2047196.2047203"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3319878"},{"key":"ref41","author":"doan","year":"2012","journal-title":"Principles of Data Integration"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2882952"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137633"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.14778\/3157794.3157797"},{"key":"ref126","first-page":"3567","article-title":"Data programming: Creating large training sets, quickly","author":"ratner","year":"2016","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref125","doi-asserted-by":"crossref","DOI":"10.1145\/2939502.2939515","article-title":"Data programming with ddlite: Putting humans in a different part of the loop","author":"ehrenberg","year":"2016","journal-title":"Proc Workshop Human-In-the-Loop Data Analytics"},{"key":"ref124","article-title":"Deepdive: A data management system for automatic knowledge base construction","author":"zhang","year":"2015"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1170"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-1083"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1145\/3329486.3329492"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806243"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3314036"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_26"},{"key":"ref76","first-page":"67","article-title":"Keyword search in relational databases: A survey","volume":"33","author":"yu","year":"2010","journal-title":"IEEE Data Eng Bulletin"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1145\/3209889.3209898"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.14778\/1687553.1687622"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1079"},{"key":"ref75","first-page":"5","article-title":"Managing google's data lake: An overview of the goods system","volume":"39","author":"halevy","year":"2016","journal-title":"IEEE Data Eng Bulletin"},{"key":"ref133","article-title":"YAGO3: A knowledge base from multilingual wikipedias","author":"mahdisoltani","year":"2015","journal-title":"Proc Biennial Conf Innovative Data Syst Res"},{"key":"ref134","first-page":"523","article-title":"Open language learning for information extraction","author":"schmitz","year":"2012","journal-title":"Proc Joint Conf Empirical Methods Natural Language Process Comput Natural Language Learn"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376746"},{"key":"ref78","first-page":"1001","article-title":"Aurum: A data discovery system","author":"fernandez","year":"2018","journal-title":"Proc IEEE 34th Int Conf Data Eng"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242667"},{"key":"ref79","first-page":"989","article-title":"Seeping semantics: Linking datasets using word embeddings for data discovery","author":"fernandez","year":"2018","journal-title":"Proc IEEE 34th Int Conf Data Eng"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1038"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2013.6606627"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.14778\/2732286.2732288"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623623"},{"key":"ref60","article-title":"Synthesizing tabular data using generative adversarial networks","volume":"abs 1811 11264","author":"xu","year":"2018","journal-title":"CoRR"},{"key":"ref139","first-page":"109","article-title":"Roadrunner: Towards automatic data extraction from large web sites","author":"crescenzi","year":"2001","journal-title":"Proc 27th Int Conf Very Large Data Bases"},{"key":"ref62","article-title":"The GAN landscape: Losses, architectures, regularization, and normalization","volume":"abs 1807 4720","author":"kurach","year":"2018","journal-title":"CoRR"},{"key":"ref61","article-title":"NIPS 2016 tutorial: Generative adversarial networks","volume":"abs 1701 160","author":"goodfellow","year":"2017","journal-title":"CoRR"},{"key":"ref63","first-page":"113","article-title":"Autoaugment: Learning augmentation policies from data","author":"cubuk","year":"2019","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref64","first-page":"3239","article-title":"Learning to compose domain-specific transformations for data augmentation","author":"ratner","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1145\/988672.988687"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.151"},{"key":"ref141","first-page":"2302","article-title":"Never-ending learning","author":"mitchell","year":"2015","journal-title":"Proc Association Advancement Artif Intell"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989232"},{"key":"ref142","first-page":"1306","article-title":"Toward an architecture for never-ending language learning","author":"carlson","year":"2010","journal-title":"Proc 24th AAAI Conf Artif Intell"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_39"},{"key":"ref143","article-title":"Semi-supervised learning literature survey","author":"zhu","year":"2008"},{"key":"ref68","article-title":"Synthetic data and artificial neural networks for natural scene text recognition","volume":"abs 1406 2227","author":"jaderberg","year":"2014","journal-title":"CoRR"},{"key":"ref144","article-title":"UCI machine learning repository","author":"dheeru","year":"2017"},{"key":"ref2","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref145","first-page":"255","article-title":"Keel data-mining software tool: Data set repository, integration of algorithms and experimental analysis framework","volume":"17","author":"alcal-fdez","year":"2010","journal-title":"Multiple-Valued Logic Soft Comput"},{"key":"ref1","article-title":"Deep learning for detection of diabetic eye disease","year":"0"},{"key":"ref109","first-page":"441","article-title":"Toward optimal active learning through sampling estimation of error reduction","author":"roy","year":"2001","journal-title":"Proc 18th Int Conf Mach Learn"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279962"},{"key":"ref108","first-page":"1289","article-title":"Multiple-instance active learning","author":"settles","year":"2007","journal-title":"Proc 20th Int Conf Neural Inf Process Syst"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2004.48"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.3115\/1613715.1613855"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2005.186"},{"key":"ref106","first-page":"1","article-title":"Query learning strategies using boosting and bagging","author":"abe","year":"1998","journal-title":"Proc 15th Int Conf Mach Learn"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.3115\/981658.981684"},{"key":"ref105","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-01560-1","author":"settles","year":"2012","journal-title":"Active Learning"},{"key":"ref91","first-page":"2825","article-title":"Scikit-learn: Machine learning in python","volume":"12","author":"pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1145\/130385.130417"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA.2016.49"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-2099-5_1"},{"key":"ref102","first-page":"940","article-title":"Scaling graph-based semi supervised learning to large number of labels using count-min sketch","author":"talukdar","year":"2014","journal-title":"Proc Int Conf Artif Intell Statistics"},{"key":"ref111","first-page":"350","article-title":"Employing em and pool-based active learning for text classification","author":"mccallum","year":"1998","journal-title":"Proc 15th Int Conf Mach Learn"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.3115\/1690219.1690291"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77226-2_22"},{"key":"ref98","article-title":"A co-regularized approach to semi-supervised learning with multiple views","author":"sindhwani","year":"2005","journal-title":"Proc ICML Workshop Learn Multiple Views"},{"key":"ref99","first-page":"908","article-title":"Semi-supervised regression with co-training","author":"zhou","year":"2005","journal-title":"Proc 19th Int Joint Conf Artif Intell"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-013-0706-y"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143862"},{"key":"ref10","article-title":"Datahub: Collaborative data science & dataset version management at scale","author":"bhardwaj","year":"2015","journal-title":"Proc Biennial Conf Innovative Data Syst Res"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.14778\/2824032.2824035"},{"key":"ref12","article-title":"Data publishing and sharing using fusion tables","author":"halevy","year":"2013","journal-title":"Proc Biennial Conf Innovative Data Syst Res"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1807128.1807158"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807286"},{"key":"ref15","article-title":"Ckan","year":"0"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.14778\/2350229.2350263"},{"key":"ref16","article-title":"Quandl","year":"0"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2013.20"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2557238"},{"key":"ref17","article-title":"Datamarket","year":"0"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1561\/1900000044"},{"key":"ref18","article-title":"Kaggle","year":"0"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2535242"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1401965"},{"key":"ref19","article-title":"Data wrangling: The challenging yourney from the wild to the lake","author":"terrizzano","year":"2015","journal-title":"Proc Biennial Conf Innovative Data Syst Res"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3148148"},{"key":"ref114","first-page":"58","article-title":"Combining active learning and semi-supervised learning using gaussian fields and harmonic functions","author":"zhu","year":"2003","journal-title":"Proc ICML Workshop Continuum Labeled Unlabeled Data Mach Learn Data Mining"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30115-8_48"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.14778\/2735471.2735474"},{"key":"ref80","first-page":"1188","article-title":"Distributed representations of sentences and documents","author":"le","year":"2014","journal-title":"Proc 31st Int Conf Int Conf Mach Learn"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3026044"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213878"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/2737817.2737819"},{"key":"ref121","first-page":"1953","article-title":"Iterative learning for reliable crowdsourcing systems","author":"karger","year":"2011","journal-title":"Proc 24th Int Conf Neural Inf Process Syst"},{"key":"ref122","article-title":"Vox populi: Collecting high-quality labels from a crowd","author":"dekel","year":"2009","journal-title":"Proc 22nd Annu Conf Learn Theory"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.14778\/2535568.2448944"},{"key":"ref85","article-title":"Amazon mechanical turk","year":"0"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998196"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998332"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2518669"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/9371488\/08862913.pdf?arnumber=8862913","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T03:03:28Z","timestamp":1664593408000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8862913\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,1]]},"references-count":187,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2019.2946162","relation":{"is-referenced-by":[{"id-type":"doi","id":"10.1186\/s40537-025-01346-9","asserted-by":"object"}]},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,1]]}}}