{"id":"https://openalex.org/W3119752913","doi":"https://doi.org/10.1145/3431816","title":"Deep Entity Matching","display_name":"Deep Entity Matching","publication_year":2021,"publication_date":"2021-01-06","ids":{"openalex":"https://openalex.org/W3119752913","doi":"https://doi.org/10.1145/3431816","mag":"3119752913"},"language":"en","primary_location":{"id":"doi:10.1145/3431816","doi":"https://doi.org/10.1145/3431816","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3431816","pdf_url":null,"source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-c","jufo-1","norway-1","poland-70","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"},"volume":null,"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/A5100750716","display_name":"Yuliang Li","orcid":"https://orcid.org/0000-0002-0602-149X","observed_orcids":["https://orcid.org/0000-0002-0602-149X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuliang Li","raw_affiliation_strings":["Megagon Labs, Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Megagon Labs, Mountain View, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428948","display_name":"Jinfeng Li","orcid":"https://orcid.org/0000-0001-9462-2625","observed_orcids":["https://orcid.org/0000-0001-9462-2625"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinfeng Li","raw_affiliation_strings":["Megagon Labs, Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Megagon Labs, Mountain View, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072690374","display_name":"Yoshihiko Suhara","orcid":"https://orcid.org/0000-0001-7554-2865","observed_orcids":["https://orcid.org/0000-0001-7554-2865"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoshihiko Suhara","raw_affiliation_strings":["Megagon Labs, Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Megagon Labs, Mountain View, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113414416","display_name":"Jin Wang","orcid":"https://orcid.org/0000-0002-8298-4378","observed_orcids":["https://orcid.org/0000-0002-8298-4378","https://orcid.org/0000-0001-5473-8738","https://orcid.org/0000-0002-8519-3301","https://orcid.org/0009-0002-9559-4288","https://orcid.org/0009-0005-9070-2448","https://orcid.org/0009-0008-0389-7227"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin Wang","raw_affiliation_strings":["Megagon Labs, Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Megagon Labs, Mountain View, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000108670","display_name":"Wataru Hirota","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wataru Hirota","raw_affiliation_strings":["Megagon Labs, Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Megagon Labs, Mountain View, CA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026007789","display_name":"Wang-Chiew Tan","orcid":"https://orcid.org/0009-0008-4174-7545","observed_orcids":["https://orcid.org/0009-0008-4174-7545"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang-Chiew Tan","raw_affiliation_strings":["Megagon Labs, Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Megagon Labs, Mountain View, CA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.2293,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.96777584,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"13","issue":"1","first_page":"1","last_page":"17"},"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/T10028","display_name":"Topic Modeling","score":9.999999747378752e-05,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.0,"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/entity-resolution","display_name":"entity resolution","score":0.9950000047683716},{"id":"https://openalex.org/keywords/ditto","display_name":"Ditto","score":0.800000011920929},{"id":"https://openalex.org/keywords/pre-trained-language-models","display_name":"pre-trained language models","score":0.9039999842643738},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"data deduplication","score":0.7580000162124634},{"id":"https://openalex.org/keywords/blocking","display_name":"blocking","score":0.6150000095367432},{"id":"https://openalex.org/keywords/training-data-requirements","display_name":"training data requirements","score":0.6299999952316284},{"id":"https://openalex.org/keywords/explainability","display_name":"explainability","score":0.6769999861717224},{"id":"https://openalex.org/keywords/data-integration","display_name":"data integration","score":0.44999998807907104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8710655570030212},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.7775533199310303},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6421631574630737},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.5455715656280518},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.5048838257789612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4995453357696533},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4784691035747528},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.42506909370422363},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3782332241535187},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32377272844314575},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.22181028127670288},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.083767831325531},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3431816","doi":"https://doi.org/10.1145/3431816","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3431816","pdf_url":null,"source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-c","jufo-1","norway-1","poland-70","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1525595230","https://openalex.org/W1731081199","https://openalex.org/W1750205245","https://openalex.org/W1843891098","https://openalex.org/W1964189668","https://openalex.org/W1981590391","https://openalex.org/W1995099886","https://openalex.org/W2007682403","https://openalex.org/W2031250218","https://openalex.org/W2059299892","https://openalex.org/W2061873838","https://openalex.org/W2073471108","https://openalex.org/W2104511295","https://openalex.org/W2114764731","https://openalex.org/W2119465010","https://openalex.org/W2129607105","https://openalex.org/W2134584261","https://openalex.org/W2152184085","https://openalex.org/W2164501930","https://openalex.org/W2165698076","https://openalex.org/W2167847032","https://openalex.org/W2479722630","https://openalex.org/W2493916176","https://openalex.org/W2508865106","https://openalex.org/W2516809705","https://openalex.org/W2542998387","https://openalex.org/W2597603852","https://openalex.org/W2758609995","https://openalex.org/W2787560479","https://openalex.org/W2798435682","https://openalex.org/W2798649495","https://openalex.org/W2804927761","https://openalex.org/W2897405591","https://openalex.org/W2898474096","https://openalex.org/W2933781133","https://openalex.org/W2945883855","https://openalex.org/W2946504770","https://openalex.org/W2948130259","https://openalex.org/W2950133940","https://openalex.org/W2950813035","https://openalex.org/W2951147191","https://openalex.org/W2951438725","https://openalex.org/W2957204582","https://openalex.org/W2957285709","https://openalex.org/W2958815962","https://openalex.org/W2962772482","https://openalex.org/W2966720878","https://openalex.org/W2968210605","https://openalex.org/W2970641574","https://openalex.org/W2970875249","https://openalex.org/W2971681342","https://openalex.org/W2978017171","https://openalex.org/W2984651502","https://openalex.org/W2985009327","https://openalex.org/W2999615587","https://openalex.org/W3010144884","https://openalex.org/W3011807731","https://openalex.org/W3013103751","https://openalex.org/W3029701880","https://openalex.org/W3033733989","https://openalex.org/W3034997167","https://openalex.org/W3086663505","https://openalex.org/W3097013020","https://openalex.org/W3101366597"],"related_works":["https://openalex.org/W3014705052","https://openalex.org/W2798649495","https://openalex.org/W6990365224","https://openalex.org/W7009717061","https://openalex.org/W4414648183","https://openalex.org/W4317039121","https://openalex.org/W3197468999","https://openalex.org/W4393166924","https://openalex.org/W6892236312","https://openalex.org/W4367357638"],"abstract_inverted_index":{"Entity":[0],"matching":[1,81,108,132,151,181,188,200],"refers":[2,49],"to":[3,13,20,38,50,80,83,156,159,183,192,198],"the":[4,14,36,51,76,130,143,154,176,185],"task":[5],"of":[6,54,72,78,104,145,168,178],"determining":[7,55,75],"whether":[8,56],"two":[9,57],"different":[10,32],"representations":[11,59],"refer":[12],"same":[15],"real-world":[16],"entity.":[17],"It":[18],"continues":[19],"be":[21,39,62],"a":[22,105],"prevalent":[23],"problem":[24,53,66],"for":[25,128],"many":[26],"organizations":[27],"where":[28],"data":[29,163],"resides":[30],"in":[31,120],"sources":[33],"and":[34,41,124,149,175],"duplicates":[35],"need":[37,155,197],"identified":[40],"managed.":[42],"The":[43],"term":[44],"\u201centity":[45],"matching\u201d":[46],"also":[47],"loosely":[48],"broader":[52,186],"heterogeneous":[58],"ofdifferent":[60],"entitiesshould":[61],"associated":[63],"together.":[64],"This":[65],"has":[67,87],"an":[68,102,193],"even":[69,194],"wider":[70],"scope":[71],"applications,":[73],"from":[74],"subsidiaries":[77],"companies":[79],"jobs":[82],"job":[84],"seekers,":[85],"which":[86,100,190],"impactful":[88],"consequences.":[89],"In":[90],"this":[91],"article,":[92],"we":[93,116,135],"first":[94],"report":[95],"our":[96],"recent":[97,118],"system":[98,109],"DITTO,":[99],"is":[101],"example":[103],"modern":[106],"entity":[107,131,140,150,180,187],"based":[110],"on":[111],"pretrained":[112],"language":[113,126,173],"models.":[114],"Then":[115],"summarize":[117],"solutions":[119,182],"applying":[121],"deep":[122,169],"learning":[123,170],"pre-trained":[125,172],"models":[127],"solving":[129],"task.":[133],"Finally,":[134],"discuss":[136],"research":[137],"directions":[138],"beyond":[139],"matching,":[141],"including":[142],"promise":[144],"synergistically":[146],"integrating":[147],"blocking":[148],"steps":[152],"together,":[153],"examine":[157],"methods":[158],"alleviate":[160],"steep":[161],"training":[162],"requirements":[164],"that":[165],"are":[166],"typical":[167],"or":[171],"models,":[174],"importance":[177],"generalizing":[179],"handle":[184],"problem,":[189],"leads":[191],"more":[195],"pressing":[196],"explain":[199],"outcomes.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":6}],"updated_date":"2026-10-22T18:32:59.640997","created_date":"2021-01-18T00:00:00"}