{"id":"https://openalex.org/W2526029773","doi":"https://doi.org/10.1145/2951894.2951909","title":"Towards High-Precision and Reusable Entity Resolution Algorithms over Sparse Financial Datasets","display_name":"Towards High-Precision and Reusable Entity Resolution Algorithms over Sparse Financial Datasets","publication_year":2016,"publication_date":"2016-06-26","ids":{"openalex":"https://openalex.org/W2526029773","doi":"https://doi.org/10.1145/2951894.2951909","mag":"2526029773"},"language":"en","primary_location":{"id":"doi:10.1145/2951894.2951909","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2951894.2951909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second International Workshop on Data Science for Macro-Modeling","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/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":true,"raw_author_name":"Douglas Burdick","raw_affiliation_strings":["IBM Almaden Research, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","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 Almaden Research, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102820528","display_name":"Rajasekar Krishnamurthy","orcid":"https://orcid.org/0000-0002-1245-4152"},"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":"Rajasekar Krishnamurthy","raw_affiliation_strings":["IBM Almaden Research, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112041087"],"corresponding_institution_ids":["https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":0.3591,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70791363,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9901000261306763,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/subroutine","display_name":"Subroutine","score":0.8085068464279175},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7925481796264648},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7174718379974365},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.678984522819519},{"id":"https://openalex.org/keywords/modulo","display_name":"Modulo","score":0.6393269300460815},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.536499559879303},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5305631160736084},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4707297086715698},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.457872599363327},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.4485177993774414},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4164765477180481},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09364363551139832}],"concepts":[{"id":"https://openalex.org/C96147967","wikidata":"https://www.wikidata.org/wiki/Q190686","display_name":"Subroutine","level":2,"score":0.8085068464279175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7925481796264648},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7174718379974365},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.678984522819519},{"id":"https://openalex.org/C54732982","wikidata":"https://www.wikidata.org/wiki/Q1415345","display_name":"Modulo","level":2,"score":0.6393269300460815},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.536499559879303},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5305631160736084},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4707297086715698},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.457872599363327},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.4485177993774414},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4164765477180481},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09364363551139832},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2951894.2951909","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2951894.2951909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second International Workshop on Data Science for Macro-Modeling","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2139021951","https://openalex.org/W2296743901"],"related_works":["https://openalex.org/W2391861012","https://openalex.org/W2488336788","https://openalex.org/W4285469493","https://openalex.org/W1593224248","https://openalex.org/W2375766869","https://openalex.org/W2080384954","https://openalex.org/W4382519933","https://openalex.org/W3151465598","https://openalex.org/W2368144149","https://openalex.org/W1590427085"],"abstract_inverted_index":{"We":[0],"describe":[1],"our":[2],"approach":[3],"to":[4,41,53],"the":[5,35,39,45,48,70,100,103,109],"FEIII":[6],"Data":[7],"Challenge,":[8],"which":[9,83],"requires":[10],"matching":[11,36],"entities":[12],"across":[13],"multiple":[14],"financial":[15],"datasets":[16],"(FFIEC,":[17],"SEC":[18],"and":[19,38,64,119,125,127,130],"LEI).":[20],"By":[21],"making":[22],"use":[23,76],"of":[24,69,77],"a":[25,58,78,87],"high-level":[26,71,95],"language":[27],"(HIL)":[28],"that":[29,102],"includes":[30],"constructs":[31],"for":[32,90],"expressing":[33],"both":[34],"logic":[37],"policies":[40],"avoid":[42],"or":[43],"reduce":[44],"ambiguities":[46],"among":[47],"matches,":[49],"we":[50,73],"are":[51],"able":[52],"produce":[54],"highly-accurate":[55],"results":[56],"in":[57,99],"sparse":[59],"context,":[60],"with":[61,86],"only":[62,116],"name":[63],"location":[65],"attributes.":[66],"As":[67],"part":[68],"specification,":[72],"also":[74,122],"make":[75],"Smart-Term":[79],"Generation":[80],"(STG)":[81],"component,":[82],"provides":[84],"us":[85],"sophisticated":[88],"subroutine":[89],"normalizing":[91],"company":[92],"names.":[93],"The":[94],"specification":[96,106],"is":[97,112],"reusable,":[98],"sense":[101],"same":[104],"HIL":[105],"(modulo":[107],"changing":[108],"attribute":[110],"names)":[111],"uniformly":[113],"applicable":[114],"not":[115],"between":[117,123,128],"FFIEC":[118,124],"SEC,":[120],"but":[121],"LEI,":[126],"LEI":[129],"SEC.":[131]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}