{"id":"https://openalex.org/W3033527224","doi":"https://doi.org/10.1145/3385188","title":"Asterisk","display_name":"Asterisk","publication_year":2020,"publication_date":"2020-05-30","ids":{"openalex":"https://openalex.org/W3033527224","doi":"https://doi.org/10.1145/3385188","mag":"3033527224"},"language":"en","primary_location":{"id":"doi:10.1145/3385188","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3385188","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3385188","source":{"id":"https://openalex.org/S4210185969","display_name":"ACM/IMS Transactions on Data Science","issn_l":"2577-3224","issn":["2577-3224","2691-1922"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM/IMS Transactions on Data Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3385188","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032311062","display_name":"Mona Nashaat","orcid":"https://orcid.org/0000-0002-7580-5757"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mona Nashaat","raw_affiliation_strings":["Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7580-5757","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022645420","display_name":"Aindrila Ghosh","orcid":"https://orcid.org/0000-0003-4908-9491"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Aindrila Ghosh","raw_affiliation_strings":["Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030495591","display_name":"James Miller","orcid":"https://orcid.org/0000-0001-5095-3000"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"James Miller","raw_affiliation_strings":["Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031825849","display_name":"Shaikh Quader","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113654","display_name":"IBM (Canada)","ror":"https://ror.org/025sxka56","country_code":"CA","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210113654"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shaikh Quader","raw_affiliation_strings":["IBM Canada Software Lab, IBM Canada, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Canada Software Lab, IBM Canada, Canada","institution_ids":["https://openalex.org/I4210113654"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6771,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.76360164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"1","issue":"2","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8012217283248901},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7213538289070129},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5901798009872437},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5786997675895691},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5465006232261658},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5247718691825867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.507750391960144},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.50105881690979},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.4385562539100647},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35566213726997375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8012217283248901},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7213538289070129},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5901798009872437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5786997675895691},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5465006232261658},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5247718691825867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.507750391960144},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.50105881690979},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.4385562539100647},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35566213726997375},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3385188","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3385188","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3385188","source":{"id":"https://openalex.org/S4210185969","display_name":"ACM/IMS Transactions on Data Science","issn_l":"2577-3224","issn":["2577-3224","2691-1922"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM/IMS Transactions on Data Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3385188","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3385188","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3385188","source":{"id":"https://openalex.org/S4210185969","display_name":"ACM/IMS Transactions on Data Science","issn_l":"2577-3224","issn":["2577-3224","2691-1922"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM/IMS Transactions on Data Science","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.550000011920929,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3033527224.pdf","grobid_xml":"https://content.openalex.org/works/W3033527224.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W2008989859","https://openalex.org/W2021732807","https://openalex.org/W2029604420","https://openalex.org/W2037866349","https://openalex.org/W2046518304","https://openalex.org/W2072576466","https://openalex.org/W2085988980","https://openalex.org/W2093040750","https://openalex.org/W2096623936","https://openalex.org/W2130486630","https://openalex.org/W2182886880","https://openalex.org/W2247875277","https://openalex.org/W2408920689","https://openalex.org/W2466758040","https://openalex.org/W2525579820","https://openalex.org/W2582409643","https://openalex.org/W2594899909","https://openalex.org/W2612526924","https://openalex.org/W2739068567","https://openalex.org/W2746791238","https://openalex.org/W2750384547","https://openalex.org/W2753688405","https://openalex.org/W2757016771","https://openalex.org/W2760375580","https://openalex.org/W2769041395","https://openalex.org/W2785494456","https://openalex.org/W2787445774","https://openalex.org/W2789758093","https://openalex.org/W2798587560","https://openalex.org/W2800615729","https://openalex.org/W2800689051","https://openalex.org/W2809611810","https://openalex.org/W2824561939","https://openalex.org/W2903158431","https://openalex.org/W2911424454","https://openalex.org/W2914456020","https://openalex.org/W2945573699","https://openalex.org/W2959716049","https://openalex.org/W2962745799","https://openalex.org/W2963696295","https://openalex.org/W2964154753","https://openalex.org/W2971225399","https://openalex.org/W4212774754","https://openalex.org/W4244238878","https://openalex.org/W4252964922","https://openalex.org/W4313371817"],"related_works":["https://openalex.org/W3126131865","https://openalex.org/W2361861616","https://openalex.org/W2044344400","https://openalex.org/W2263699433","https://openalex.org/W4253186488","https://openalex.org/W2377979023","https://openalex.org/W1996938127","https://openalex.org/W2083611981","https://openalex.org/W2218034408","https://openalex.org/W2392921965"],"abstract_inverted_index":{"Labeling":[0],"datasets":[1,165],"is":[2,43],"one":[3],"of":[4,39,101,108,118,127,158,166,173,182],"the":[5,37,40,73,84,93,98,102,106,109,113,116,119,125,128,132,152,180,183],"most":[6],"expensive":[7],"bottlenecks":[8],"in":[9,13,18,46,185],"data":[10],"preprocessing":[11],"tasks":[12],"machine":[14],"learning.":[15],"Therefore,":[16,45],"organizations,":[17],"many":[19],"domains,":[20],"are":[21],"applying":[22],"weak":[23,31],"supervision":[24,32],"to":[25,56,68,82,123],"produce":[26],"noisy":[27],"labels.":[28,71,129],"However,":[29],"since":[30],"relies":[33],"on":[34],"cheaper":[35],"sources,":[36],"quality":[38,126],"generated":[41],"labels":[42,188],"problematic.":[44],"this":[47],"article,":[48],"we":[49,135,150],"present":[50,88],"Asterisk":[51],",":[52],"an":[53,89],"end-to-end":[54],"framework":[55,74,153,184],"generate":[57],"high-quality,":[58],"large-scale":[59],"labeled":[60],"datasets.":[61],"The":[62,161,177],"system,":[63,134],"first,":[64],"automatically":[65],"generates":[66],"heuristics":[67],"assign":[69],"initial":[70],"Then,":[72],"applies":[75],"a":[76,155,170],"novel":[77],"data-driven":[78],"active":[79,120],"learning":[80,121],"process":[81,122],"enhance":[83,124],"labeling":[85],"quality.":[86],"We":[87],"algorithm":[90],"that":[91],"learns":[92],"selection":[94],"policy":[95],"by":[96],"accommodating":[97],"modeled":[99],"accuracies":[100],"heuristics,":[103],"along":[104],"with":[105,145,169,194],"outcome":[107],"generative":[110],"model.":[111],"Finally,":[112],"system":[114],"employs":[115],"output":[117],"To":[130],"evaluate":[131],"proposed":[133],"report":[136],"its":[137],"performance":[138],"against":[139],"four":[140],"state-of-the-art":[141],"techniques.":[142],"In":[143],"collaboration":[144],"our":[146],"industrial":[147],"partner,":[148],"IBM,":[149],"test":[151],"within":[154],"wide":[156],"range":[157],"real-world":[159],"applications.":[160],"experiments":[162],"include":[163],"10":[164],"varying":[167],"sizes":[168],"maximum":[171],"size":[172],"11":[174],"million":[175],"records.":[176],"results":[178],"illustrate":[179],"effectiveness":[181],"producing":[186],"high-quality":[187],"and":[189],"achieving":[190],"high":[191],"classification":[192],"accuracy":[193],"minimal":[195],"annotation":[196],"efforts.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2020-06-12T00:00:00"}