{"id":"https://openalex.org/W2886633187","doi":"https://doi.org/10.1145/3242153.3242156","title":"Improving Machine-based Entity Resolution with Limited Human Effort","display_name":"Improving Machine-based Entity Resolution with Limited Human Effort","publication_year":2018,"publication_date":"2018-08-27","ids":{"openalex":"https://openalex.org/W2886633187","doi":"https://doi.org/10.1145/3242153.3242156","mag":"2886633187"},"language":"en","primary_location":{"id":"doi:10.1145/3242153.3242156","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3242153.3242156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on Real-Time Business Intelligence and Analytics","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1805.12502","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhaoqiang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhaoqiang Chen","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, China and Key Laboratory of Big Data Storage and Management, NPU, MIIT, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, China and Key Laboratory of Big Data Storage and Management, NPU, MIIT, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qun Chen","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, China and Key Laboratory of Big Data Storage and Management, NPU, MIIT, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, China and Key Laboratory of Big Data Storage and Management, NPU, MIIT, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Boyi Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyi Hou","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, China and Key Laboratory of Big Data Storage and Management, NPU, MIIT, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, China and Key Laboratory of Big Data Storage and Management, NPU, MIIT, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Murtadha Ahmed","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Murtadha Ahmed","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, China and Key Laboratory of Big Data Storage and Management, NPU, MIIT, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, China and Key Laboratory of Big Data Storage and Management, NPU, MIIT, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhanhuai Li","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanhuai Li","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, China and Key Laboratory of Big Data Storage and Management, NPU, MIIT, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, China and Key Laboratory of Big Data Storage and Management, NPU, MIIT, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.2201,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.60929369,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9914000034332275,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9819999933242798,"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/crowdsourcing","display_name":"Crowdsourcing","score":0.6848000288009644},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.6664999723434448},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4984000027179718},{"id":"https://openalex.org/keywords/risk-management","display_name":"Risk management","score":0.2912999987602234},{"id":"https://openalex.org/keywords/low-resolution","display_name":"Low resolution","score":0.2849000096321106}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745199978351593},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.6848000288009644},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.6664999723434448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5425000190734863},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5390999913215637},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4984000027179718},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40880000591278076},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.31459999084472656},{"id":"https://openalex.org/C32896092","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Risk management","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C3019883945","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Low resolution","level":3,"score":0.2849000096321106},{"id":"https://openalex.org/C3020199158","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"High resolution","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3242153.3242156","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3242153.3242156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on Real-Time Business Intelligence and Analytics","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1805.12502","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.12502","pdf_url":"https://arxiv.org/pdf/1805.12502","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1805.12502","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.12502","pdf_url":"https://arxiv.org/pdf/1805.12502","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2056748234","https://openalex.org/W2067566391","https://openalex.org/W2292361954","https://openalex.org/W2428834396","https://openalex.org/W2548695521","https://openalex.org/W2579968393","https://openalex.org/W2775696413","https://openalex.org/W3124407081"],"related_works":[],"abstract_inverted_index":{"Pure":[0],"machine-based":[1,44],"solutions":[2],"usually":[3],"struggle":[4],"in":[5,27],"the":[6,25,28,33,56,73,97,103,111,114,129,137,142,157],"challenging":[7,40],"classification":[8],"tasks":[9],"such":[10],"as":[11,100,102],"entity":[12,45],"resolution":[13,29,46,154],"(ER).":[14],"To":[15],"alleviate":[16],"this":[17,52,86],"problem,":[18],"a":[19,66,90],"recent":[20],"trend":[21],"is":[22],"to":[23,41,71],"involve":[24],"human":[26,49,59,146],"process,":[30],"most":[31],"notably":[32],"crowdsourcing":[34],"approach.":[35],"However,":[36],"it":[37,125,149],"remains":[38],"very":[39],"effectively":[42],"improve":[43],"with":[47,132,141],"limited":[48],"effort.":[50],"In":[51],"paper,":[53],"we":[54,88,109],"investigate":[55],"problem":[57],"of":[58,79,105,113,145],"and":[60],"machine":[61,106],"cooperation":[62],"for":[63,82],"ER":[64],"from":[65],"risk":[67,78,91,116],"perspective.":[68],"We":[69],"propose":[70],"select":[72],"machine-labeled":[74],"instances":[75,99,131],"at":[76],"high":[77],"being":[80],"mislabeled":[81,130],"manual":[83],"verification.":[84],"For":[85],"task,":[87],"present":[89],"model":[92,117],"that":[93,124],"takes":[94],"into":[95],"consideration":[96],"human-labeled":[98],"well":[101],"output":[104],"resolution.":[107],"Finally,":[108],"evaluate":[110],"performance":[112],"proposed":[115],"on":[118,161],"real":[119],"data.":[120],"Our":[121],"experiments":[122],"demonstrate":[123],"can":[126,150],"pick":[127],"up":[128],"considerably":[133],"higher":[134],"accuracy":[135],"than":[136,156],"existing":[138],"alternatives.":[139],"Provided":[140],"same":[143],"amount":[144],"cost":[147],"budget,":[148],"also":[151],"achieve":[152],"better":[153],"quality":[155],"state-of-the-art":[158],"approach":[159],"based":[160],"active":[162],"learning.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2018-08-22T00:00:00"}