{"id":"https://openalex.org/W2074409795","doi":"https://doi.org/10.1145/1376616.1376742","title":"Incorporating string transformations in record matching","display_name":"Incorporating string transformations in record matching","publication_year":2008,"publication_date":"2008-06-09","ids":{"openalex":"https://openalex.org/W2074409795","doi":"https://doi.org/10.1145/1376616.1376742","mag":"2074409795"},"language":"en","primary_location":{"id":"doi:10.1145/1376616.1376742","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1376616.1376742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 ACM SIGMOD international conference on Management of data","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/A5026802346","display_name":"Arvind Arasu","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Arvind Arasu","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038037154","display_name":"Surajit Chaudhuri","orcid":"https://orcid.org/0000-0001-8252-5270"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Surajit Chaudhuri","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080534589","display_name":"Kris Ganjam","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kris Ganjam","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103280746","display_name":"Raghav Kaushik","orcid":"https://orcid.org/0000-0003-1457-1384"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghav Kaushik","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5026802346"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":2.5447,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.89603676,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1231","last_page":"1234"},"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":0.9900000095367432,"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":0.9843999743461609,"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/approximate-string-matching","display_name":"Approximate string matching","score":0.8592218160629272},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.7293462157249451},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.698811411857605},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6890173554420471},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6839132308959961},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6574164628982544},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.638387143611908},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5305773615837097},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.5301870703697205},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4652387201786041},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4483897089958191},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.4465055465698242},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4210791289806366},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4184590280056},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3216277062892914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2725374102592468},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2113303542137146},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10170218348503113},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08608430624008179}],"concepts":[{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.8592218160629272},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.7293462157249451},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.698811411857605},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6890173554420471},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6839132308959961},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6574164628982544},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.638387143611908},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5305773615837097},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.5301870703697205},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4652387201786041},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4483897089958191},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.4465055465698242},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4210791289806366},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4184590280056},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3216277062892914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2725374102592468},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2113303542137146},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10170218348503113},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08608430624008179},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1376616.1376742","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1376616.1376742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6299999952316284,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1502916507","https://openalex.org/W2007682403","https://openalex.org/W2032327675","https://openalex.org/W2072173758","https://openalex.org/W2096598900","https://openalex.org/W6629956336","https://openalex.org/W6674576723"],"related_works":["https://openalex.org/W2257399947","https://openalex.org/W2371263218","https://openalex.org/W2141423589","https://openalex.org/W2386746909","https://openalex.org/W2399644331","https://openalex.org/W2037600093","https://openalex.org/W2245915510","https://openalex.org/W2366300241","https://openalex.org/W3145288231","https://openalex.org/W2130362787"],"abstract_inverted_index":{"Today's":[0],"record":[1,40,86,107],"matching":[2,41,108],"infrastructure":[3],"does":[4],"not":[5],"allow":[6],"a":[7,75,88],"flexible":[8],"way":[9],"to":[10,21,42,60,82],"account":[11],"for":[12],"synonyms":[13],"such":[14,32,44],"as":[15,33,48,100],"\"Robert\"":[16],"and":[17,25,110],"\"Bob\"":[18],"which":[19],"refer":[20],"the":[22,37,62,69],"same":[23],"name,":[24],"more":[26],"general":[27],"forms":[28],"of":[29,39,71,90,98,121],"string":[30,46],"transformations":[31,47,51,99],"abbreviations.":[34],"We":[35,67,102],"expand":[36],"problem":[38],"take":[43],"user-defined":[45],"input.":[49,101],"These":[50],"coupled":[52],"with":[53],"an":[54,84,95,104],"underlying":[55],"similarity":[56,63],"function":[57],"are":[58],"used":[59,81],"define":[61],"between":[64],"two":[65],"strings.":[66],"demonstrate":[68,103],"effectiveness":[70],"this":[72],"approach":[73],"via":[74],"fuzzy":[76],"match":[77],"operation":[78],"that":[79,118],"is":[80,119],"lookup":[83],"input":[85],"against":[87],"table":[89,97],"records,":[91],"where":[92],"we":[93],"have":[94],"additional":[96],"improvement":[105],"in":[106],"quality":[109],"efficient":[111],"retrieval":[112],"based":[113],"on":[114],"our":[115],"index":[116],"structure":[117],"cognizant":[120],"transformations.":[122]},"counts_by_year":[{"year":2019,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}