{"id":"https://openalex.org/W3080592272","doi":"https://doi.org/10.1145/3405962.3405964","title":"Using schema.org Annotations for Training and Maintaining Product Matchers","display_name":"Using schema.org Annotations for Training and Maintaining Product Matchers","publication_year":2020,"publication_date":"2020-06-30","ids":{"openalex":"https://openalex.org/W3080592272","doi":"https://doi.org/10.1145/3405962.3405964","mag":"3080592272"},"language":"en","primary_location":{"id":"doi:10.1145/3405962.3405964","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3405962.3405964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th International Conference on Web Intelligence, Mining and Semantics","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/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":["Data and Web Science Group, University of Mannheim, Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data and Web Science Group, University of Mannheim, Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]},{"author_position":"middle","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":false,"raw_author_name":"Anna Primpeli","raw_affiliation_strings":["Data and Web Science Group, University of Mannheim, Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data and Web Science Group, University of Mannheim, Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041404377","display_name":"Benedikt Wichtlhuber","orcid":null},"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":"Benedikt Wichtlhuber","raw_affiliation_strings":["Data and Web Science Group, University of Mannheim, Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data and Web Science Group, University of Mannheim, Mannheim, Germany","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":["Data and Web Science Group, University of Mannheim, Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data and Web Science Group, University of Mannheim, Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177802217"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"195","last_page":"204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.998199999332428,"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/T10028","display_name":"Topic Modeling","score":0.9940000176429749,"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":0.7802029848098755},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.7405369877815247},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6800371408462524},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5360143184661865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5218485593795776},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4782252013683319},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4693542420864105},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.419399231672287},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.355265349149704},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.31430065631866455},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.19819840788841248}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7802029848098755},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.7405369877815247},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6800371408462524},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5360143184661865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5218485593795776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4782252013683319},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4693542420864105},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.419399231672287},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.355265349149704},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31430065631866455},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.19819840788841248},{"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":2,"locations":[{"id":"doi:10.1145/3405962.3405964","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3405962.3405964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th International Conference on Web Intelligence, Mining and Semantics","raw_type":"proceedings-article"},{"id":"pmh:oai:ub-madoc.bib.uni-mannheim.de:56262","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.1145/3405962.3405964","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":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1981590391","https://openalex.org/W2024105308","https://openalex.org/W2043437843","https://openalex.org/W2045968013","https://openalex.org/W2073471108","https://openalex.org/W2108991785","https://openalex.org/W2160024037","https://openalex.org/W2413794162","https://openalex.org/W2493916176","https://openalex.org/W2521135474","https://openalex.org/W2542998387","https://openalex.org/W2747329762","https://openalex.org/W2752172973","https://openalex.org/W2763940251","https://openalex.org/W2798649495","https://openalex.org/W2807329228","https://openalex.org/W2889910479","https://openalex.org/W2893314940","https://openalex.org/W2903678049","https://openalex.org/W2945883855","https://openalex.org/W2946457832","https://openalex.org/W2946524278","https://openalex.org/W2951147191","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2966720878","https://openalex.org/W2967627683","https://openalex.org/W2990816204","https://openalex.org/W2997591727","https://openalex.org/W3010144884","https://openalex.org/W3011807731","https://openalex.org/W3012733951","https://openalex.org/W3099883947","https://openalex.org/W3101157305","https://openalex.org/W3123375411","https://openalex.org/W6726709572"],"related_works":["https://openalex.org/W2471940468","https://openalex.org/W113172935","https://openalex.org/W3208717180","https://openalex.org/W2406112091","https://openalex.org/W2125859764","https://openalex.org/W2014400548","https://openalex.org/W4301779090","https://openalex.org/W2029826694","https://openalex.org/W4298139853","https://openalex.org/W1990272589"],"abstract_inverted_index":{"Product":[0],"matching":[1,20,72,94,143,161,172,214],"is":[2,51,140,227],"a":[3,75],"central":[4],"task":[5],"within":[6],"e-commerce":[7,80],"applications":[8],"such":[9,47],"as":[10,53,60,193,197,202],"price":[11],"comparison":[12],"portals":[13],"and":[14,45,127,170,177,182,212,222],"online":[15],"market":[16],"places.":[17],"State-of-the-art":[18],"product":[19,71,93,132],"methods":[21],"achieve":[22,122],"F1":[23,123],"scores":[24,124],"above":[25],"0.90":[26],"using":[27,112,189,198],"deep":[28,168,210,225],"learning":[29,169,211,226],"techniques":[30],"combined":[31],"with":[32,148,179,216,231],"huge":[33],"amounts":[34,233],"of":[35,42,58,89,167,234],"training":[36,49,90,194],"data":[37,91,115],"(e.g":[38],">":[39],"100K":[40],"pairs":[41,57],"offers).":[43],"Gathering":[44],"maintaining":[46],"large":[48],"corpora":[50],"costly,":[52],"it":[54,139],"implies":[55],"labeling":[56,88],"offers":[59],"matches":[61],"or":[62],"non-matches.":[63],"Acquiring":[64],"the":[65,86,106,131,165,199,232],"ability":[66],"to":[67,121,153,159,218,229],"be":[68,96,146],"good":[69],"at":[70],"thus":[73],"means":[74],"major":[76],"investment":[77],"for":[78,92,116,185],"an":[79],"company.":[81],"This":[82],"paper":[83],"shows":[84],"that":[85,111,142,224],"manual":[87],"can":[95,145],"replaced":[97],"by":[98],"relying":[99],"exclusively":[100],"on":[101,130,157,174],"schema.org":[102,114,191,238],"annotations":[103,192],"gathered":[104],"from":[105],"public":[107,200],"Web.":[108],"We":[109],"show":[110,223],"only":[113,190],"training,":[117],"we":[118,163,208],"are":[119],"able":[120,228],"between":[125],"0.92":[126],"0.95":[128],"depending":[129],"category.":[133],"As":[134],"new":[135],"products":[136,176],"appear":[137],"everyday,":[138],"important":[141],"models":[144,173,215],"maintained":[147],"justifiable":[149],"effort.":[150],"In":[151],"order":[152],"give":[154],"practical":[155],"advice":[156],"how":[158],"maintain":[160],"models,":[162],"compare":[164],"performance":[166],"traditional":[171,213],"unseen":[175],"experiment":[178],"different":[180],"fine-tuning":[181],"re-training":[183],"strategies":[184],"model":[186],"maintenance,":[187],"again":[188],"data.":[195],"Finally,":[196],"Web":[201],"distant":[203],"supervision":[204],"carries":[205],"inherent":[206],"noise,":[207],"evaluate":[209],"regards":[217],"their":[219],"label-noise":[220],"resistance":[221],"deal":[230],"identifier-noise":[235],"found":[236],"in":[237],"annotations.":[239]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}