{"id":"https://openalex.org/W2043437843","doi":"https://doi.org/10.1145/2247596.2247662","title":"Tailoring entity resolution for matching product offers","display_name":"Tailoring entity resolution for matching product offers","publication_year":2012,"publication_date":"2012-03-27","ids":{"openalex":"https://openalex.org/W2043437843","doi":"https://doi.org/10.1145/2247596.2247662","mag":"2043437843"},"language":"en","primary_location":{"id":"doi:10.1145/2247596.2247662","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2247596.2247662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Extending Database Technology","raw_type":"proceedings-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/A5077091793","display_name":"Hanna K\u00f6pcke","orcid":"https://orcid.org/0000-0003-2501-2609"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hanna K\u00f6pcke","raw_affiliation_strings":["Web Data Integration Lab, Leipzig, Germany"],"affiliations":[{"raw_affiliation_string":"Web Data Integration Lab, Leipzig, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015557906","display_name":"Andreas Thor","orcid":"https://orcid.org/0000-0003-2575-2893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Thor","raw_affiliation_strings":["Web Data Integration Lab, Leipzig, Germany"],"affiliations":[{"raw_affiliation_string":"Web Data Integration Lab, Leipzig, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055082405","display_name":"Stefan Thomas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Thomas","raw_affiliation_strings":["Web Data Integration Lab, Leipzig, Germany"],"affiliations":[{"raw_affiliation_string":"Web Data Integration Lab, Leipzig, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075756237","display_name":"Erhard Rahm","orcid":"https://orcid.org/0000-0002-2665-1114"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erhard Rahm","raw_affiliation_strings":["Web Data Integration Lab, Leipzig, Germany"],"affiliations":[{"raw_affiliation_string":"Web Data Integration Lab, Leipzig, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077091793"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.2796,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.97552645,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"545","last_page":"550"},"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":0.9848999977111816,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9847000241279602,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7644141912460327},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.7394170761108398},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.7232800722122192},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.7153509855270386},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5717847943305969},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.44419580698013306},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41339111328125},{"id":"https://openalex.org/keywords/product-type","display_name":"Product type","score":0.41028687357902527},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40851733088493347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28426218032836914},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.11402979493141174},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11043384671211243}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7644141912460327},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.7394170761108398},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.7232800722122192},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.7153509855270386},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5717847943305969},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.44419580698013306},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41339111328125},{"id":"https://openalex.org/C23219732","wikidata":"https://www.wikidata.org/wiki/Q7247800","display_name":"Product type","level":2,"score":0.41028687357902527},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40851733088493347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28426218032836914},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.11402979493141174},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11043384671211243},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2247596.2247662","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2247596.2247662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Extending Database Technology","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.225.9013","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.225.9013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dbs.uni-leipzig.de/file/edbt2012_final.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1646278814","https://openalex.org/W1969221592","https://openalex.org/W1981590391","https://openalex.org/W2045968013","https://openalex.org/W2104511295","https://openalex.org/W2108991785","https://openalex.org/W2125101870","https://openalex.org/W2149364369","https://openalex.org/W2164180916","https://openalex.org/W2170039925"],"related_works":["https://openalex.org/W2982321410","https://openalex.org/W95465806","https://openalex.org/W2392004567","https://openalex.org/W2940029036","https://openalex.org/W2756595502","https://openalex.org/W2010789764","https://openalex.org/W2219281195","https://openalex.org/W2187233292","https://openalex.org/W2532162280","https://openalex.org/W82655570"],"abstract_inverted_index":{"Product":[0,19],"matching":[1,20,59],"is":[2,21,128],"a":[3,62,80],"challenging":[4,109],"variation":[5],"of":[6,29,45,54,64,104],"entity":[7],"resolution":[8],"to":[9,15,25,67,83,90,134],"identify":[10,91],"representations":[11],"and":[12,41,48,69,85,93,131],"offers":[13,66,114,127],"referring":[14],"the":[16,26,42,52,102,105,122],"same":[17],"product.":[18],"highly":[22],"difficult":[23],"due":[24],"broad":[27],"spectrum":[28],"products,":[30,35],"many":[31],"similar":[32,97],"but":[33],"different":[34],"frequently":[36],"missing":[37],"or":[38],"wrong":[39],"values,":[40],"textual":[43],"nature":[44],"product":[46,58,65,88,98,113,126],"titles":[47],"descriptions.":[49],"We":[50,100,118],"propose":[51,79],"use":[53,86],"tailored":[55],"approaches":[56,107],"for":[57,74],"based":[60],"on":[61],"preprocessing":[63],"extract":[68,84],"clean":[70],"new":[71,81],"attributes":[72],"usable":[73],"matching.":[75],"In":[76],"particular,":[77],"we":[78],"approach":[82],"so-called":[87],"codes":[89],"products":[92],"distinguish":[94],"them":[95],"from":[96,115],"variations.":[99],"evaluate":[101],"effectiveness":[103],"proposed":[106],"with":[108,112],"real-life":[110],"datasets":[111],"online":[116],"shops.":[117],"also":[119],"show":[120],"that":[121],"UPC":[123],"information":[124],"in":[125],"often":[129],"error-prone":[130],"can":[132],"lead":[133],"insufficient":[135],"match":[136],"decisions.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
