{"id":"https://openalex.org/W4290943621","doi":"https://doi.org/10.1145/3534678.3547352","title":"Large-Scale Information Extraction under Privacy-Aware Constraints","display_name":"Large-Scale Information Extraction under Privacy-Aware Constraints","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4290943621","doi":"https://doi.org/10.1145/3534678.3547352"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3547352","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3547352","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079361910","display_name":"Rajeev Gupta","orcid":"https://orcid.org/0000-0002-0685-474X"},"institutions":[{"id":"https://openalex.org/I4210162141","display_name":"Microsoft (India)","ror":"https://ror.org/04ww0w091","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210162141"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Rajeev Gupta","raw_affiliation_strings":["Microsoft, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Microsoft, Hyderabad, India","institution_ids":["https://openalex.org/I4210162141"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016105675","display_name":"Ranganath Kondapally","orcid":"https://orcid.org/0000-0003-4625-1051"},"institutions":[{"id":"https://openalex.org/I4210162141","display_name":"Microsoft (India)","ror":"https://ror.org/04ww0w091","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210162141"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ranganath Kondapally","raw_affiliation_strings":["Microsoft, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Microsoft, Hyderabad, India","institution_ids":["https://openalex.org/I4210162141"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079361910"],"corresponding_institution_ids":["https://openalex.org/I4210162141"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10788863,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"4792","last_page":"4793"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9991999864578247,"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/T11719","display_name":"Data Quality and Management","score":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8341947793960571},{"id":"https://openalex.org/keywords/differential-privacy","display_name":"Differential privacy","score":0.7584539651870728},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7070978283882141},{"id":"https://openalex.org/keywords/nobody","display_name":"nobody","score":0.6964228749275208},{"id":"https://openalex.org/keywords/private-information-retrieval","display_name":"Private information retrieval","score":0.5852891206741333},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.5270369648933411},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.5049167275428772},{"id":"https://openalex.org/keywords/personally-identifiable-information","display_name":"Personally identifiable information","score":0.4913005232810974},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4596651792526245},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4520055651664734},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4442141652107239},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4167880713939667},{"id":"https://openalex.org/keywords/privacy-software","display_name":"Privacy software","score":0.4120427966117859},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4088289141654968},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3293517231941223},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.29735636711120605},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.27918970584869385},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.19713395833969116}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8341947793960571},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.7584539651870728},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7070978283882141},{"id":"https://openalex.org/C36914074","wikidata":"https://www.wikidata.org/wiki/Q1940501","display_name":"nobody","level":2,"score":0.6964228749275208},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.5852891206741333},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.5270369648933411},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.5049167275428772},{"id":"https://openalex.org/C169093310","wikidata":"https://www.wikidata.org/wiki/Q3702971","display_name":"Personally identifiable information","level":2,"score":0.4913005232810974},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4596651792526245},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4520055651664734},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4442141652107239},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4167880713939667},{"id":"https://openalex.org/C509729295","wikidata":"https://www.wikidata.org/wiki/Q7246032","display_name":"Privacy software","level":3,"score":0.4120427966117859},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4088289141654968},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3293517231941223},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.29735636711120605},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27918970584869385},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.19713395833969116},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political 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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3534678.3547352","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3547352","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W133884053","https://openalex.org/W1630959083","https://openalex.org/W1980176056","https://openalex.org/W2038967169","https://openalex.org/W2076362672","https://openalex.org/W2107391405","https://openalex.org/W2134150392","https://openalex.org/W2165698076","https://openalex.org/W2255862008","https://openalex.org/W2340222647","https://openalex.org/W2808874433","https://openalex.org/W2903158431","https://openalex.org/W2947774097","https://openalex.org/W2967042743","https://openalex.org/W2998093075","https://openalex.org/W3175753977","https://openalex.org/W4235216760","https://openalex.org/W4365799834","https://openalex.org/W6638523607","https://openalex.org/W6644074671","https://openalex.org/W6678138319"],"related_works":["https://openalex.org/W3213134179","https://openalex.org/W3124980542","https://openalex.org/W2886969487","https://openalex.org/W3210561385","https://openalex.org/W3041348913","https://openalex.org/W1945159329","https://openalex.org/W113555067","https://openalex.org/W1608514471","https://openalex.org/W2908470827","https://openalex.org/W4296598554"],"abstract_inverted_index":{"In":[0,204],"this":[1,14,30,64,127,205],"digital":[2],"age,":[3],"people":[4],"spend":[5],"a":[6,103,172,188,197,200],"significant":[7],"portion":[8],"of":[9,20,23,77,106,113,175,191,214],"their":[10,27,54],"lives":[11],"online":[12],"and":[13,34,50,69,133,187,223],"has":[15],"led":[16],"to":[17,26,42,59,88,92,100,118,140,153,217],"an":[18],"explosion":[19],"personal":[21],"data":[22,31,87,108,114,121,178,194,216],"users":[24,52],"due":[25,91],"activities.":[28],"Typically,":[29],"is":[32,40,57,85,115],"private":[33,120,215],"nobody":[35],"else,":[36],"except":[37],"the":[38,149,211,221],"user,":[39],"allowed":[41],"look":[43],"at":[44],"it.":[45],"To":[46],"provide":[47],"better":[48],"experience":[49],"assist":[51],"in":[53,219],"activities,":[55],"it":[56,156],"critical":[58],"mine":[60],"certain":[61],"information":[62,74,80,159,227],"from":[63,72,90,143],"data.":[65,125],"This":[66],"poses":[67],"interesting":[68],"complex":[70,136],"challenge":[71],"scalable":[73,226],"extraction":[75,81,169,228],"point":[76],"view:":[78],"building":[79,168],"models":[82,99,170],"where":[83],"there":[84],"little":[86],"learn":[89],"privacy":[93,138,181],"constraints":[94],"but":[95],"need":[96],"highly":[97],"accurate":[98],"run":[101],"on":[102],"large":[104,189],"amount":[105,174,190],"diverse":[107],"across":[109],"different":[110],"users.":[111],"Anonymization":[112],"typically":[116],"used":[117],"convert":[119],"into":[122],"publicly":[123],"accessible":[124],"But":[126],"may":[128,134],"not":[129],"always":[130],"be":[131,141,185],"feasible":[132],"require":[135],"differential":[137],"guarantees":[139],"safe":[142],"any":[144],"potential":[145],"negative":[146],"consequences.":[147],"Further,":[148],"anonymization":[150],"process":[151],"needs":[152],"ensure":[154],"that":[155],"retains":[157],"sufficient":[158],"for":[160,225],"modeling":[161],"purposes":[162],"post":[163],"anonymization.":[164],"Other":[165],"techniques":[166],"involve":[167],"using":[171],"small":[173],"seen":[176],"(eyes-on)":[177],"with":[179],"no":[180],"restrictions":[182],"(hence,":[183],"can":[184,202],"labeled)":[186],"unseen":[192],"(eyes-off)":[193],"which":[195],"only":[196],"machine":[198],"or":[199],"program":[201],"access.":[203],"tutorial,":[206],"we":[207],"use":[208],"emails":[209],"as":[210],"canonical":[212],"example":[213],"explain":[218],"detail":[220],"challenges":[222],"solutions":[224],"(IE)":[229],"under":[230],"privacy-aware":[231],"constraints.":[232]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}