{"id":"https://openalex.org/W2945883855","doi":"https://doi.org/10.1145/3308560.3316609","title":"The WDC Training Dataset and Gold Standard for Large-Scale Product Matching","display_name":"The WDC Training Dataset and Gold Standard for Large-Scale Product Matching","publication_year":2019,"publication_date":"2019-05-13","ids":{"openalex":"https://openalex.org/W2945883855","doi":"https://doi.org/10.1145/3308560.3316609","mag":"2945883855"},"language":"en","primary_location":{"id":"doi:10.1145/3308560.3316609","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308560.3316609","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of The 2019 World Wide Web Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3308560.3316609","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010968230","display_name":"Anna Primpeli","orcid":"https://orcid.org/0000-0002-1783-2482"},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Anna Primpeli","raw_affiliation_strings":["University of Mannheim"],"affiliations":[{"raw_affiliation_string":"University of Mannheim","institution_ids":["https://openalex.org/I177802217"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082603069","display_name":"Ralph Peeters","orcid":"https://orcid.org/0000-0003-3174-2616"},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralph Peeters","raw_affiliation_strings":["University of Mannheim"],"affiliations":[{"raw_affiliation_string":"University of Mannheim","institution_ids":["https://openalex.org/I177802217"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076876024","display_name":"Christian Bizer","orcid":"https://orcid.org/0000-0003-2367-0237"},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Bizer","raw_affiliation_strings":["University of Mannheim"],"affiliations":[{"raw_affiliation_string":"University of Mannheim","institution_ids":["https://openalex.org/I177802217"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010968230"],"corresponding_institution_ids":["https://openalex.org/I177802217"],"apc_list":null,"apc_paid":null,"fwci":6.38,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":{"value":0.96523625,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"381","last_page":"386"},"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/T10028","display_name":"Topic Modeling","score":0.9840999841690063,"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":0.9819999933242798,"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":0.806915283203125},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.6603758335113525},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6572007536888123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.622400164604187},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5648569464683533},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5446871519088745},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4821424186229706},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4524475634098053},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4507293403148651},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42393958568573},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34757906198501587},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08130857348442078},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07602271437644958}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.806915283203125},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.6603758335113525},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6572007536888123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.622400164604187},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5648569464683533},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5446871519088745},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4821424186229706},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4524475634098053},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4507293403148651},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42393958568573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34757906198501587},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08130857348442078},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07602271437644958},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3308560.3316609","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308560.3316609","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of The 2019 World Wide Web Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:ub-madoc.bib.uni-mannheim.de:49930","is_oa":false,"landing_page_url":"https://madoc.bib.uni-mannheim.de/49930/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196315","display_name":"MADOC (University of Mannheim)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177802217","host_organization_name":"University of Mannheim","host_organization_lineage":["https://openalex.org/I177802217"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"}],"best_oa_location":{"id":"doi:10.1145/3308560.3316609","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308560.3316609","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of The 2019 World Wide Web Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1981590391","https://openalex.org/W2045968013","https://openalex.org/W2107966677","https://openalex.org/W2126890920","https://openalex.org/W2160024037","https://openalex.org/W2268509563","https://openalex.org/W2295639288","https://openalex.org/W2296045323","https://openalex.org/W2474883156","https://openalex.org/W2480535768","https://openalex.org/W2542998387","https://openalex.org/W2589049294","https://openalex.org/W2612526608","https://openalex.org/W2745153524","https://openalex.org/W2798649495","https://openalex.org/W2807329228","https://openalex.org/W2885625746"],"related_works":["https://openalex.org/W4254851101","https://openalex.org/W3171007296","https://openalex.org/W22115721","https://openalex.org/W2211931904","https://openalex.org/W2065444835","https://openalex.org/W2321234655","https://openalex.org/W2952773340","https://openalex.org/W2470062578","https://openalex.org/W2981861370","https://openalex.org/W2982204590"],"abstract_inverted_index":{"A":[0],"current":[1],"research":[2],"question":[3,41],"in":[4,20],"the":[5,64,94,106,169],"area":[6],"of":[7,51,75,93,98,102,124,144,154,172],"entity":[8,55],"resolution":[9,56],"(also":[10],"called":[11],"link":[12],"discovery":[13],"or":[14,131],"duplicate":[15],"detection)":[16],"is":[17,42],"whether":[18],"and":[19,24,178],"which":[21,117],"cases":[22],"embeddings":[23,177],"deep":[25,44,179],"neural":[26,180],"network":[27,181],"based":[28,46,182],"matching":[29,34,76,183,188],"methods":[30,184,189],"outperform":[31,185],"traditional":[32,186],"symbolic":[33,187],"methods.":[35,77],"The":[36,54,78,89,109],"problem":[37],"with":[38,159],"answering":[39],"this":[40,72,87,160],"that":[43,59,176],"learning":[45],"matchers":[47],"need":[48],"large":[49],"amounts":[50],"training":[52,95,156],"data.":[53,193],"benchmark":[57],"datasets":[58],"are":[60,66,164],"currently":[61],"available":[62],"to":[63,69,105,147,166],"public":[65],"too":[67],"small":[68],"properly":[70],"evaluate":[71],"new":[73],"family":[74],"WDC":[79],"Training":[80],"Dataset":[81],"for":[82],"Large-Scale":[83],"Product":[84],"Matching":[85],"fills":[86],"gap.":[88],"English":[90],"language":[91],"subset":[92,153],"dataset":[96,157],"consists":[97],"20":[99],"million":[100],"pairs":[101,143],"offers":[103,110,145],"referring":[104],"same":[107],"products.":[108],"were":[111],"extracted":[112],"from":[113],"43":[114],"thousand":[115],"e-shops":[116],"provide":[118],"schema.org":[119],"annotations":[120],"including":[121],"some":[122],"form":[123],"product":[125,149],"ID":[126],"such":[127],"as":[128],"a":[129,136,152],"GTIN":[130],"MPN.":[132],"We":[133],"also":[134],"created":[135],"gold":[137,161],"standard":[138],"by":[139],"manually":[140],"verifying":[141],"2200":[142],"belonging":[146],"four":[148],"categories.":[150],"Using":[151],"our":[155],"together":[158],"standard,":[162],"we":[163],"able":[165],"publicly":[167],"replicate":[168],"recent":[170],"result":[171],"Mudgal":[173],"et":[174],"al.":[175],"on":[190],"less":[191],"structured":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":6}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}