{"id":"https://openalex.org/W3093671642","doi":"https://doi.org/10.1145/3340531.3412131","title":"Schema-Agnostic Entity Matching using Pre-trained Language Models","display_name":"Schema-Agnostic Entity Matching using Pre-trained Language Models","publication_year":2020,"publication_date":"2020-10-19","ids":{"openalex":"https://openalex.org/W3093671642","doi":"https://doi.org/10.1145/3340531.3412131","mag":"3093671642"},"language":"en","primary_location":{"id":"doi:10.1145/3340531.3412131","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340531.3412131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5075334906","display_name":"Kai-Sheng Teong","orcid":null},"institutions":[{"id":"https://openalex.org/I11662577","display_name":"Monash University Malaysia","ror":"https://ror.org/00yncr324","country_code":"MY","type":"education","lineage":["https://openalex.org/I11662577"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Kai-Sheng Teong","raw_affiliation_strings":["Monash University Malaysia, Subang Jaya, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University Malaysia, Subang Jaya, Malaysia","institution_ids":["https://openalex.org/I11662577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069570912","display_name":"Lay-Ki Soon","orcid":"https://orcid.org/0000-0002-8072-242X"},"institutions":[{"id":"https://openalex.org/I11662577","display_name":"Monash University Malaysia","ror":"https://ror.org/00yncr324","country_code":"MY","type":"education","lineage":["https://openalex.org/I11662577"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Lay-Ki Soon","raw_affiliation_strings":["Monash University Malaysia, Subang Jaya, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University Malaysia, Subang Jaya, Malaysia","institution_ids":["https://openalex.org/I11662577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082146947","display_name":"Tin Tin Su","orcid":"https://orcid.org/0000-0003-0387-6406"},"institutions":[{"id":"https://openalex.org/I11662577","display_name":"Monash University Malaysia","ror":"https://ror.org/00yncr324","country_code":"MY","type":"education","lineage":["https://openalex.org/I11662577"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Tin Tin Su","raw_affiliation_strings":["Monash University Malaysia, Subang Jaya, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University Malaysia, Subang Jaya, Malaysia","institution_ids":["https://openalex.org/I11662577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I11662577"],"apc_list":null,"apc_paid":null,"fwci":4.0937,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.95618039,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2241","last_page":"2244"},"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/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9794999957084656,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8373361825942993},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.7521535754203796},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.7292612791061401},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5417540669441223},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.5394732356071472},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5390057563781738},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5291857123374939},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4838484823703766},{"id":"https://openalex.org/keywords/star-schema","display_name":"Star schema","score":0.4811040759086609},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4142211377620697},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41077935695648193},{"id":"https://openalex.org/keywords/database-schema","display_name":"Database schema","score":0.3965630531311035},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.19710540771484375},{"id":"https://openalex.org/keywords/database-design","display_name":"Database design","score":0.10057151317596436}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8373361825942993},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.7521535754203796},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.7292612791061401},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5417540669441223},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.5394732356071472},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5390057563781738},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5291857123374939},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4838484823703766},{"id":"https://openalex.org/C190703929","wikidata":"https://www.wikidata.org/wiki/Q1331138","display_name":"Star schema","level":4,"score":0.4811040759086609},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4142211377620697},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41077935695648193},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.3965630531311035},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.19710540771484375},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.10057151317596436},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3340531.3412131","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340531.3412131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1547612978","https://openalex.org/W2043437843","https://openalex.org/W2250539671","https://openalex.org/W2493916176","https://openalex.org/W2542998387","https://openalex.org/W2612732335","https://openalex.org/W2769488050","https://openalex.org/W2798649495","https://openalex.org/W2893314940","https://openalex.org/W2946031341","https://openalex.org/W2946504770","https://openalex.org/W2963716420","https://openalex.org/W3145232008","https://openalex.org/W4234053595","https://openalex.org/W4295330703"],"related_works":["https://openalex.org/W2376319089","https://openalex.org/W2034415381","https://openalex.org/W2546483132","https://openalex.org/W2351507151","https://openalex.org/W2107807087","https://openalex.org/W2373484664","https://openalex.org/W1528218860","https://openalex.org/W2766698234","https://openalex.org/W3030019037","https://openalex.org/W945629821"],"abstract_inverted_index":{"Entity":[0],"matching":[1],"(EM)":[2],"is":[3,89,122,166,191],"the":[4,45,59,64,97],"process":[5],"of":[6,22,25,63,73,99,159,173,178,182],"linking":[7],"records":[8],"from":[9,96],"different":[10,171],"data":[11],"sources.":[12],"While":[13],"extensive":[14],"research":[15],"has":[16],"been":[17],"done":[18],"in":[19,44,102,112,161,167],"various":[20],"aspects":[21],"EM,":[23,84],"many":[24],"these":[26],"studies":[27],"generally":[28],"assume":[29],"EM":[30,50,105],"tasks":[31],"as":[32],"schema-specific,":[33],"which":[34],"attempt":[35],"to":[36,107],"match":[37],"record":[38],"pairs":[39],"at":[40],"attributes":[41,67],"level.":[42],"Unfortunately,":[43],"real-world,":[46],"tables":[47,88,103],"that":[48,151,187],"undergo":[49],"may":[51],"not":[52,69,90],"have":[53],"an":[54,79,157],"aligned":[55],"schema,":[56],"and":[57,66,138,145],"often,":[58],"schema":[60],"or":[61],"metadata":[62],"table":[65],"are":[68],"known":[70],"beforehand.In":[71],"view":[72],"this":[74,76],"challenge,":[75],"paper":[77],"presents":[78],"effective":[80],"approach":[81],"for":[82,104,180,193],"schema-agnostic":[83],"where":[85],"having":[86],"schema-aligned":[87],"compulsory.":[91],"The":[92,130,147,164],"proposed":[93,131,153,189],"method":[94,132],"stemmed":[95],"idea":[98],"treating":[100],"tuples":[101],"similar":[106],"sentence":[108],"pair":[109],"classification":[110],"problem":[111],"natural":[113],"language":[114,119],"processing":[115],"(NLP).":[116],"A":[117],"pre-trained":[118],"model,":[120],"BERT":[121],"adopted":[123],"by":[124,156],"fine-tuning":[125],"it":[126],"using":[127,135],"labeled":[128],"dataset.":[129],"was":[133],"experimented":[134],"benchmark":[136],"datasets":[137],"compared":[139],"against":[140],"two":[141],"state-of-the-art":[142],"approaches,namely":[143],"DeepMatcher":[144],"Magellan.":[146],"experimental":[148],"results":[149],"show":[150],"our":[152,188],"solution":[154,190],"outperforms":[155],"average":[158],"9%":[160],"F1":[162],"score.":[163],"performance":[165],"fact":[168],"consistent":[169],"across":[170],"types":[172],"datasets,":[174],"showing":[175],"significant":[176],"improvement":[177],"29.6%":[179],"one":[181],"dirty":[183],"datasets.":[184],"These":[185],"prove":[186],"versatile":[192],"EM.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}