{"id":"https://openalex.org/W3174036215","doi":"https://doi.org/10.1145/3448016.3457258","title":"Rotom","display_name":"Rotom","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3174036215","doi":"https://doi.org/10.1145/3448016.3457258","mag":"3174036215"},"language":"en","primary_location":{"id":"doi:10.1145/3448016.3457258","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3448016.3457258","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3457258","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3457258","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087858861","display_name":"Zhengjie Miao","orcid":"https://orcid.org/0009-0008-2371-1186"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhengjie Miao","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100750716","display_name":"Yuliang Li","orcid":"https://orcid.org/0000-0002-0602-149X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuliang Li","raw_affiliation_strings":["Megagon Labs, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Megagon Labs, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100767225","display_name":"Xiaolan Wang","orcid":"https://orcid.org/0000-0002-2293-5160"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaolan Wang","raw_affiliation_strings":["Megagon Labs, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Megagon Labs, Mountain View, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087858861"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":7.5354,"has_fulltext":true,"cited_by_count":57,"citation_normalized_percentile":{"value":0.97614718,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1303","last_page":"1316"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9793000221252441,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9790999889373779,"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":0.7943511605262756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5588986277580261},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5577956438064575},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5443141460418701},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5119977593421936},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.5033130049705505},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.495475172996521},{"id":"https://openalex.org/keywords/novelty-detection","display_name":"Novelty detection","score":0.45334550738334656},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4339020550251007},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.377417653799057}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7943511605262756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5588986277580261},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5577956438064575},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5443141460418701},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5119977593421936},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.5033130049705505},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.495475172996521},{"id":"https://openalex.org/C2778924833","wikidata":"https://www.wikidata.org/wiki/Q7064603","display_name":"Novelty detection","level":3,"score":0.45334550738334656},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4339020550251007},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.377417653799057},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3448016.3457258","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3448016.3457258","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3457258","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3448016.3457258","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3448016.3457258","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3457258","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4213323792","display_name":null,"funder_award_id":"1552538","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5559452935","display_name":null,"funder_award_id":"2008107","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3174036215.pdf","grobid_xml":"https://content.openalex.org/works/W3174036215.grobid-xml"},"referenced_works_count":85,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1610496399","https://openalex.org/W1923344279","https://openalex.org/W1992479406","https://openalex.org/W2013666871","https://openalex.org/W2035615211","https://openalex.org/W2038721957","https://openalex.org/W2041439319","https://openalex.org/W2044469685","https://openalex.org/W2047745978","https://openalex.org/W2052698082","https://openalex.org/W2067566391","https://openalex.org/W2111625757","https://openalex.org/W2119320829","https://openalex.org/W2119717200","https://openalex.org/W2119803607","https://openalex.org/W2133236963","https://openalex.org/W2145680191","https://openalex.org/W2153579005","https://openalex.org/W2163605009","https://openalex.org/W2167333415","https://openalex.org/W2170240176","https://openalex.org/W2213275763","https://openalex.org/W2295333720","https://openalex.org/W2404544029","https://openalex.org/W2444650685","https://openalex.org/W2525739395","https://openalex.org/W2542998387","https://openalex.org/W2548122763","https://openalex.org/W2549035799","https://openalex.org/W2591700809","https://openalex.org/W2604763608","https://openalex.org/W2610871042","https://openalex.org/W2612139288","https://openalex.org/W2612526608","https://openalex.org/W2612925715","https://openalex.org/W2751134959","https://openalex.org/W2769041395","https://openalex.org/W2795089200","https://openalex.org/W2798649495","https://openalex.org/W2810075754","https://openalex.org/W2903158431","https://openalex.org/W2911424454","https://openalex.org/W2915915402","https://openalex.org/W2929941791","https://openalex.org/W2946504770","https://openalex.org/W2948145720","https://openalex.org/W2949736877","https://openalex.org/W2949888546","https://openalex.org/W2962369866","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2966211635","https://openalex.org/W2966720878","https://openalex.org/W2970395278","https://openalex.org/W2970971581","https://openalex.org/W2971252690","https://openalex.org/W2972830778","https://openalex.org/W2978017171","https://openalex.org/W2978426779","https://openalex.org/W2980282514","https://openalex.org/W2985009327","https://openalex.org/W2996287690","https://openalex.org/W2996501936","https://openalex.org/W2998184481","https://openalex.org/W3001197829","https://openalex.org/W3004437239","https://openalex.org/W3008440336","https://openalex.org/W3010144884","https://openalex.org/W3012733951","https://openalex.org/W3014705052","https://openalex.org/W3035682985","https://openalex.org/W3037852608","https://openalex.org/W3082197983","https://openalex.org/W3082274269","https://openalex.org/W3082424964","https://openalex.org/W3101980583","https://openalex.org/W3105771849","https://openalex.org/W3105977086","https://openalex.org/W3123375411","https://openalex.org/W4324144449","https://openalex.org/W6636177537","https://openalex.org/W6737095236","https://openalex.org/W6780165651","https://openalex.org/W6912781991"],"related_works":["https://openalex.org/W2064636555","https://openalex.org/W1939982668","https://openalex.org/W2585503716","https://openalex.org/W2076090200","https://openalex.org/W4312933423","https://openalex.org/W3025682415","https://openalex.org/W2081173909","https://openalex.org/W4382317424","https://openalex.org/W1532481220","https://openalex.org/W2604316291"],"abstract_inverted_index":{"Deep":[0],"Learning":[1],"revolutionizes":[2],"almost":[3],"all":[4],"fields":[5],"of":[6,48,56,75,114],"computer":[7],"science":[8],"including":[9,81],"data":[10,18,30,69,76,84,174],"management.":[11],"However,":[12],"the":[13,46,53,135,169,178],"demand":[14],"for":[15,72,125,189],"high-quality":[16],"training":[17],"is":[19,116],"slowing":[20],"down":[21],"deep":[22],"neural":[23],"nets'":[24],"wider":[25],"adoption.":[26],"To":[27],"this":[28,165],"end,":[29],"augmentation":[31,70],"(DA),":[32],"which":[33],"generates":[34,97],"more":[35],"labeled":[36],"examples":[37,51,102,127],"from":[38,128],"existing":[39],"ones,":[40],"becomes":[41],"a":[42,67,73,92,107,117,123,146],"common":[43],"technique.":[44],"Meanwhile,":[45],"risk":[47],"creating":[49],"noisy":[50],"and":[52,78,86,173],"large":[54],"space":[55],"hyper-parameters":[57,136],"make":[58],"DA":[59,94,105,130,152,187],"less":[60],"attractive":[61],"in":[62,177],"practice.":[63],"We":[64],"introduce":[65],"Rotom,":[66],"multi-purpose":[68],"framework":[71,119],"range":[74],"management":[77],"mining":[79],"tasks":[80],"entity":[82,171],"matching,":[83],"cleaning,":[85],"text":[87,190],"classification.":[88,191],"Rotom":[89,115,143,167],"features":[90],"InvDA,":[91],"new":[93],"operator":[95],"that":[96,120,142],"natural":[98],"yet":[99],"diverse":[100],"augmented":[101],"by":[103,149],"formulating":[104],"as":[106,181,183],"seq2seq":[108],"task.":[109],"The":[110],"key":[111],"technical":[112],"novelty":[113],"meta-learning":[118],"automatically":[121],"learns":[122],"policy":[124],"combining":[126,150],"different":[129],"operators,":[131,153],"whereby":[132],"combinatorially":[133],"reduces":[134],"space.":[137],"Our":[138],"experimental":[139],"results":[140],"show":[141],"effectively":[144],"improves":[145],"model's":[147],"performance":[148,162],"multiple":[151],"even":[154],"when":[155],"applying":[156],"them":[157],"individually":[158],"does":[159],"not":[160],"yield":[161],"improvement.":[163],"With":[164],"strength,":[166],"outperforms":[168],"state-of-the-art":[170],"matching":[172],"cleaning":[175],"systems":[176],"low-resource":[179],"settings":[180],"well":[182],"two":[184],"recently":[185],"proposed":[186],"techniques":[188]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2021-07-05T00:00:00"}