{"id":"https://openalex.org/W2958815962","doi":"https://doi.org/10.1145/3336499.3338010","title":"Learning Explainable Entity Resolution Algorithms for Small Business Data using SystemER","display_name":"Learning Explainable Entity Resolution Algorithms for Small Business Data using SystemER","publication_year":2019,"publication_date":"2019-06-30","ids":{"openalex":"https://openalex.org/W2958815962","doi":"https://doi.org/10.1145/3336499.3338010","mag":"2958815962"},"language":"en","primary_location":{"id":"doi:10.1145/3336499.3338010","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3336499.3338010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Workshop on Data Science for Macro-modeling with Financial and Economic Datasets","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/A5005099484","display_name":"Kun Qian","orcid":"https://orcid.org/0000-0002-6765-9446"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kun Qian","raw_affiliation_strings":["IBM Research - Almaden"],"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112041087","display_name":"Douglas Burdick","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas Burdick","raw_affiliation_strings":["IBM Research - Almaden"],"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005866714","display_name":"Sairam Gurajada","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sairam Gurajada","raw_affiliation_strings":["IBM Research - Almaden"],"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041152581","display_name":"Lucian Popa","orcid":"https://orcid.org/0000-0002-0659-9144"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lucian Popa","raw_affiliation_strings":["IBM Research - Almaden"],"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005099484"],"corresponding_institution_ids":["https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":0.3961,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66724489,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9900000095367432,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9850000143051147,"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":0.8166738748550415},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7211720943450928},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6949714422225952},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.6707872748374939},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5018856525421143},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.498798131942749},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46111392974853516},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4438551366329193},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.4276803135871887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4248695969581604},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40490424633026123},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.18669423460960388},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07607626914978027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8166738748550415},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7211720943450928},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6949714422225952},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.6707872748374939},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5018856525421143},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.498798131942749},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46111392974853516},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4438551366329193},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.4276803135871887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4248695969581604},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40490424633026123},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.18669423460960388},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07607626914978027},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3336499.3338010","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3336499.3338010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Workshop on Data Science for Macro-modeling with Financial and Economic Datasets","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.6100000143051147,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2139021951","https://openalex.org/W2767681556","https://openalex.org/W2828440316","https://openalex.org/W2898603644","https://openalex.org/W2951147191","https://openalex.org/W2970875249"],"related_works":["https://openalex.org/W4398232961","https://openalex.org/W3037187668","https://openalex.org/W4234772502","https://openalex.org/W2750075801","https://openalex.org/W3164948662","https://openalex.org/W4400413234","https://openalex.org/W3153597579","https://openalex.org/W4385336128","https://openalex.org/W4394398790","https://openalex.org/W4399455186"],"abstract_inverted_index":{"The":[0],"2019":[1],"FEIII":[2,143],"CALI":[3,144],"data":[4,25,83,145],"challenge":[5,37],"aims":[6],"at":[7],"linking":[8],"different":[9],"representations":[10],"of":[11,47,76,86],"the":[12,45,138,142],"same":[13],"real-world":[14],"entities":[15],"across":[16],"multiple":[17],"public":[18],"datasets":[19,139],"that":[20,59],"collect":[21],"identification":[22],"and":[23,54,67,78,91,116],"activity":[24],"about":[26],"small":[27,61],"to":[28,50,105],"medium":[29],"enterprises":[30],"(SMEs)":[31],"in":[32],"California.":[33],"We":[34],"formalize":[35],"this":[36,95],"as":[38,82],"a":[39,52,74,118],"learning-based":[40],"entity":[41,63],"resolution":[42],"(ER)":[43],"task,":[44,96],"goal":[46],"which":[48],"is":[49],"learn":[51,106,125],"high-precision":[53],"high-recall":[55],"pair-wise":[56],"ER":[57,70,107,128],"model":[58,92],"classifies":[60],"business":[62],"pairs":[64],"into":[65],"matches":[66],"non-matches.":[68],"Realistic":[69],"tasks":[71],"usually":[72],"involve":[73],"pipeline":[75],"laborintensive":[77],"error-prone":[79],"tasks,":[80],"such":[81],"preprocesing,":[84],"gathering":[85],"training":[87],"data,":[88],"feature":[89],"engineering,":[90],"tuning.":[93],"In":[94],"we":[97],"apply":[98],"an":[99],"advanced":[100],"human-in-the-loop":[101],"system,":[102],"named":[103],"SystemER,":[104],"algorithms":[108,129],"for":[109],"SME":[110],"entities.":[111],"Powered":[112],"by":[113,141],"active":[114],"learning":[115],"via":[117],"carefully":[119],"designed":[120],"user":[121],"interface,":[122],"SystemER":[123],"can":[124],"high-quality":[126],"explainable":[127],"with":[130],"low":[131],"human":[132],"effort,":[133],"while":[134],"achieving":[135],"high-accuracy":[136],"on":[137],"provided":[140],"challenge.":[146]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}