{"id":"https://openalex.org/W822439496","doi":"https://doi.org/10.18653/v1/w13-5010","title":"Graph-based Approaches for Organization Entity Resolution in MapReduce","display_name":"Graph-based Approaches for Organization Entity Resolution in MapReduce","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W822439496","doi":"https://doi.org/10.18653/v1/w13-5010","mag":"822439496"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w13-5010","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w13-5010","pdf_url":"https://aclanthology.org/W13-5010.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of TextGraphs-8 Graph-based Methods for Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W13-5010.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038628557","display_name":"Hakan Kardes","orcid":null},"institutions":[{"id":"https://openalex.org/I174135032","display_name":"Bellevue College","ror":"https://ror.org/05gr4yv49","country_code":"US","type":"education","lineage":["https://openalex.org/I174135032"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hakan Kardes","raw_affiliation_strings":["inome Inc. Bellevue , WA , USA","New York University, New York, United States"],"affiliations":[{"raw_affiliation_string":"inome Inc. Bellevue , WA , USA","institution_ids":["https://openalex.org/I174135032"]},{"raw_affiliation_string":"New York University, New York, United States","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081401265","display_name":"Deepak Konidena","orcid":null},"institutions":[{"id":"https://openalex.org/I174135032","display_name":"Bellevue College","ror":"https://ror.org/05gr4yv49","country_code":"US","type":"education","lineage":["https://openalex.org/I174135032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deepak Konidena","raw_affiliation_strings":["inome Inc. Bellevue , WA , USA"],"affiliations":[{"raw_affiliation_string":"inome Inc. Bellevue , WA , USA","institution_ids":["https://openalex.org/I174135032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018019178","display_name":"Siddharth Agrawal","orcid":"https://orcid.org/0000-0002-6068-1253"},"institutions":[{"id":"https://openalex.org/I174135032","display_name":"Bellevue College","ror":"https://ror.org/05gr4yv49","country_code":"US","type":"education","lineage":["https://openalex.org/I174135032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Agrawal","raw_affiliation_strings":["inome Inc. Bellevue , WA , USA"],"affiliations":[{"raw_affiliation_string":"inome Inc. Bellevue , WA , USA","institution_ids":["https://openalex.org/I174135032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022297513","display_name":"Micah Huff","orcid":null},"institutions":[{"id":"https://openalex.org/I174135032","display_name":"Bellevue College","ror":"https://ror.org/05gr4yv49","country_code":"US","type":"education","lineage":["https://openalex.org/I174135032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Micah Huff","raw_affiliation_strings":["inome Inc. Bellevue , WA , USA"],"affiliations":[{"raw_affiliation_string":"inome Inc. Bellevue , WA , USA","institution_ids":["https://openalex.org/I174135032"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002868174","display_name":"Ang Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I174135032","display_name":"Bellevue College","ror":"https://ror.org/05gr4yv49","country_code":"US","type":"education","lineage":["https://openalex.org/I174135032"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ang Sun","raw_affiliation_strings":["inome Inc. Bellevue , WA , USA","New York University, New York, United States"],"affiliations":[{"raw_affiliation_string":"inome Inc. Bellevue , WA , USA","institution_ids":["https://openalex.org/I174135032"]},{"raw_affiliation_string":"New York University, New York, United States","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5038628557"],"corresponding_institution_ids":["https://openalex.org/I174135032","https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":2.9875,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.90895576,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"70","last_page":"78"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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":0.9879999756813049,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9697999954223633,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7984863519668579},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7184308171272278},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6926295757293701},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5144815444946289},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.5137971043586731},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.47746542096138},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.46336859464645386},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.380524218082428},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31153589487075806},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2906150817871094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7984863519668579},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7184308171272278},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6926295757293701},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5144815444946289},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.5137971043586731},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.47746542096138},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.46336859464645386},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.380524218082428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31153589487075806},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2906150817871094},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/w13-5010","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w13-5010","pdf_url":"https://aclanthology.org/W13-5010.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of TextGraphs-8 Graph-based Methods for Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.401.1666","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.401.1666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology/W/W13/W13-5010.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.711.2343","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.711.2343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.unr.edu/%7Ehkardes/pdfs/organizationEntityResolution.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/w13-5010","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w13-5010","pdf_url":"https://aclanthology.org/W13-5010.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of TextGraphs-8 Graph-based Methods for Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W822439496.pdf","grobid_xml":"https://content.openalex.org/works/W822439496.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W106711128","https://openalex.org/W1612155886","https://openalex.org/W2027393969","https://openalex.org/W2031250218","https://openalex.org/W2036216970","https://openalex.org/W2042458413","https://openalex.org/W2079971532","https://openalex.org/W2088008685","https://openalex.org/W2107976925","https://openalex.org/W2108991785","https://openalex.org/W2111116800","https://openalex.org/W2112912553","https://openalex.org/W2117974736","https://openalex.org/W2126399065","https://openalex.org/W2128661986","https://openalex.org/W2158047102","https://openalex.org/W2166988329","https://openalex.org/W2171574281","https://openalex.org/W2295665070","https://openalex.org/W2397525010"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2942366970","https://openalex.org/W2807634898","https://openalex.org/W1692008701","https://openalex.org/W3161390536","https://openalex.org/W1540269031","https://openalex.org/W154872207"],"abstract_inverted_index":{"Entity":[0],"Resolution":[1],"is":[2,105],"the":[3,14,22,53,59,80,86,89,93,115,138],"task":[4],"of":[5,27,47,68,98,126,140],"identifying":[6],"which":[7,45],"records":[8,39,48,69,81,95,99],"in":[9],"a":[10,63,73,77,109,123,131,148],"database":[11,125],"refer":[12],"to":[13,43,66,84,121,129],"same":[15,87],"entity.A":[16],"standard":[17],"machine":[18],"learning":[19],"pipeline":[20],"for":[21,143],"entity":[23],"resolution":[24],"problem":[25],"consists":[26],"three":[28],"major":[29,132],"components:":[30],"blocking,":[31],"pairwise":[32,54],"linkage,":[33],"and":[34,117],"clustering.The":[35],"blocking":[36,116],"step":[37,61,91],"groups":[38],"by":[40,52],"shared":[41],"properties":[42],"determine":[44],"pairs":[46,67],"should":[49],"be":[50],"examined":[51],"linker":[55],"as":[56],"potential":[57],"duplicates.Next,":[58],"linkage":[60],"assigns":[62],"probability":[64],"score":[65],"inside":[70],"each":[71,103],"block.If":[72],"pair":[74],"scores":[75],"above":[76],"user-defined":[78],"threshold,":[79],"are":[82],"presumed":[83],"represent":[85],"entity.Finally,":[88],"clustering":[90,118],"turns":[92],"input":[94],"into":[96],"clusters":[97],"(or":[100],"profiles),":[101],"where":[102],"cluster":[104],"uniquely":[106],"associated":[107],"with":[108],"single":[110],"real-world":[111],"entity.This":[112],"paper":[113],"describes":[114],"strategies":[119],"used":[120],"deploy":[122],"massive":[124],"organization":[127],"entities":[128],"power":[130],"commercial":[133],"People":[134],"Search":[135],"Engine.We":[136],"demonstrate":[137],"viability":[139],"these":[141],"algorithms":[142],"large":[144],"data":[145],"sets":[146],"on":[147],"50-node":[149],"hadoop":[150],"cluster.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}