{"id":"https://openalex.org/W2885625746","doi":"https://doi.org/10.3233/sw-180300","title":"A machine learning approach for product matching and categorization","display_name":"A machine learning approach for product matching and categorization","publication_year":2018,"publication_date":"2018-08-10","ids":{"openalex":"https://openalex.org/W2885625746","doi":"https://doi.org/10.3233/sw-180300","mag":"2885625746"},"language":"en","primary_location":{"id":"doi:10.3233/sw-180300","is_oa":false,"landing_page_url":"https://doi.org/10.3233/sw-180300","pdf_url":null,"source":{"id":"https://openalex.org/S4210177235","display_name":"Semantic Web","issn_l":"1570-0844","issn":["1570-0844","2210-4968"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Semantic Web","raw_type":"journal-article"},"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/A5045816451","display_name":"Petar Ristoski","orcid":"https://orcid.org/0000-0002-1890-1507"},"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":"Petar Ristoski","raw_affiliation_strings":["Data and Web Science Group, University of Mannheim, B6, 26, 68159 Mannheim, Germany. E-mails:\u00a0petar.ristoski@informatik.uni-mannheim.de,\u00a0petar@informatik.uni-mannheim.de,\u00a0heiko@informatik.uni-mannheim.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data and Web Science Group, University of Mannheim, B6, 26, 68159 Mannheim, Germany. E-mails:\u00a0petar.ristoski@informatik.uni-mannheim.de,\u00a0petar@informatik.uni-mannheim.de,\u00a0heiko@informatik.uni-mannheim.de","institution_ids":["https://openalex.org/I177802217"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018057749","display_name":"Petar Petrovski","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":"Petar Petrovski","raw_affiliation_strings":["Data and Web Science Group, University of Mannheim, B6, 26, 68159 Mannheim, Germany. E-mails:\u00a0petar.ristoski@informatik.uni-mannheim.de,\u00a0petar@informatik.uni-mannheim.de,\u00a0heiko@informatik.uni-mannheim.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data and Web Science Group, University of Mannheim, B6, 26, 68159 Mannheim, Germany. E-mails:\u00a0petar.ristoski@informatik.uni-mannheim.de,\u00a0petar@informatik.uni-mannheim.de,\u00a0heiko@informatik.uni-mannheim.de","institution_ids":["https://openalex.org/I177802217"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036340022","display_name":"Peter Mika","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Mika","raw_affiliation_strings":["Yahoo Labs, London, UK. E-mail:\u00a0pmika@yahoo-inc.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Labs, London, UK. E-mail:\u00a0pmika@yahoo-inc.com","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040542771","display_name":"Heiko Paulheim","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":"Heiko Paulheim","raw_affiliation_strings":["Data and Web Science Group, University of Mannheim, B6, 26, 68159 Mannheim, Germany. E-mails:\u00a0petar.ristoski@informatik.uni-mannheim.de,\u00a0petar@informatik.uni-mannheim.de,\u00a0heiko@informatik.uni-mannheim.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data and Web Science Group, University of Mannheim, B6, 26, 68159 Mannheim, Germany. E-mails:\u00a0petar.ristoski@informatik.uni-mannheim.de,\u00a0petar@informatik.uni-mannheim.de,\u00a0heiko@informatik.uni-mannheim.de","institution_ids":["https://openalex.org/I177802217"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5045816451"],"corresponding_institution_ids":["https://openalex.org/I177802217"],"apc_list":null,"apc_paid":null,"fwci":4.2587,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.95355157,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"9","issue":"5","first_page":"707","last_page":"728"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9983000159263611,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9959999918937683,"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/categorization","display_name":"Categorization","score":0.7941237688064575},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7684125900268555},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6749112606048584},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.5605871677398682},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.554416298866272},{"id":"https://openalex.org/keywords/microdata","display_name":"Microdata (statistics)","score":0.542141854763031},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5210351943969727},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5082221031188965},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45975279808044434},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44022107124328613},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43632227182388306},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42588362097740173},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41432344913482666},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3534744083881378},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33327093720436096},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09304389357566833}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7941237688064575},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7684125900268555},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6749112606048584},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.5605871677398682},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.554416298866272},{"id":"https://openalex.org/C2778355071","wikidata":"https://www.wikidata.org/wiki/Q1933849","display_name":"Microdata (statistics)","level":4,"score":0.542141854763031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5210351943969727},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5082221031188965},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45975279808044434},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44022107124328613},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43632227182388306},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42588362097740173},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41432344913482666},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3534744083881378},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33327093720436096},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09304389357566833},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C52130261","wikidata":"https://www.wikidata.org/wiki/Q39825","display_name":"Census","level":3,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/sw-180300","is_oa":false,"landing_page_url":"https://doi.org/10.3233/sw-180300","pdf_url":null,"source":{"id":"https://openalex.org/S4210177235","display_name":"Semantic Web","issn_l":"1570-0844","issn":["1570-0844","2210-4968"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Semantic Web","raw_type":"journal-article"},{"id":"pmh:oai:ub-madoc.bib.uni-mannheim.de:45960","is_oa":false,"landing_page_url":"https://madoc.bib.uni-mannheim.de/45960/","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":"Zeitschriftenartikel"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W155236017","https://openalex.org/W1969221592","https://openalex.org/W1985902122","https://openalex.org/W2003661472","https://openalex.org/W2021354639","https://openalex.org/W2024105308","https://openalex.org/W2027731328","https://openalex.org/W2043437843","https://openalex.org/W2045968013","https://openalex.org/W2076063813","https://openalex.org/W2084413241","https://openalex.org/W2096765155","https://openalex.org/W2117130368","https://openalex.org/W2131462252","https://openalex.org/W2132568467","https://openalex.org/W2147458937","https://openalex.org/W2147800946","https://openalex.org/W2149364369","https://openalex.org/W2153579005","https://openalex.org/W2155169782","https://openalex.org/W2160024037","https://openalex.org/W2163605009","https://openalex.org/W2192572088","https://openalex.org/W2200092826","https://openalex.org/W2238917604","https://openalex.org/W2250539671","https://openalex.org/W2293569829","https://openalex.org/W2295145075","https://openalex.org/W2295639288","https://openalex.org/W2296045323","https://openalex.org/W2314598940","https://openalex.org/W2407521136","https://openalex.org/W2409897154","https://openalex.org/W2460313383","https://openalex.org/W3099726625","https://openalex.org/W3213320387","https://openalex.org/W4301213493"],"related_works":["https://openalex.org/W3124882577","https://openalex.org/W2045945431","https://openalex.org/W3121353175","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3167935049","https://openalex.org/W3103566983","https://openalex.org/W3029198973"],"abstract_inverted_index":{"Consumers":[0],"today":[1],"have":[2],"the":[3,13,16,20,25,33,52,109,140,143,174],"option":[4],"to":[5,99,122,149,164],"purchase":[6],"products":[7,26],"from":[8,103,126,168],"thousands":[9],"of":[10,15,113,129,142],"e-shops.":[11,30],"However,":[12],"completeness":[14],"product":[17,49,79,89,105,132,151,169],"specifications":[18],"and":[19,68,81,153],"taxonomies":[21],"used":[22],"for":[23,39,48,78,93,111,115],"organizing":[24],"differ":[27],"across":[28],"different":[29,45],"To":[31,107],"improve":[32,173],"consumer":[34],"experience,":[35],"e.g.,":[36],"by":[37,44],"allowing":[38],"easily":[40],"comparing":[41],"off":[42],"ers":[43],"vendors,":[46],"approaches":[47,77],"integration":[50],"on":[51,176],"Web":[53],"are":[54],"needed.":[55],"In":[56,83],"this":[57],"paper,":[58],"we":[59,86,117,157],"present":[60],"an":[61],"approach":[62,85],"that":[63],"leverages":[64],"neural":[65,119],"language":[66,120],"models":[67,97,121],"deep":[69,160],"learning":[70],"techniques":[71],"in":[72],"combination":[73],"with":[74,136],"standard":[75],"classification":[76],"matching":[80,152],"categorization.":[82],"our":[84],"use":[87,118,158],"structured":[88],"data":[90,114,133],"as":[91],"supervision":[92],"training":[94],"feature":[95,144],"extraction":[96,145],"able":[98],"extract":[100],"attribute-value":[101],"pairs":[102],"textual":[104],"descriptions.":[106],"minimize":[108],"need":[110],"lots":[112],"supervision,":[116],"produce":[123,165],"word":[124],"embeddings":[125,167],"large":[127],"quantities":[128],"publicly":[130],"available":[131],"marked":[134],"up":[135],"Microdata,":[137],"which":[138,171],"boost":[139],"performance":[141],"model,":[146],"thus":[147],"leading":[148],"better":[150],"categorization":[154],"performances.":[155],"Furthermore,":[156],"a":[159],"Convolutional":[161],"Neural":[162],"Network":[163],"image":[166],"images,":[170],"further":[172],"results":[175],"both":[177],"tasks.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}