{"id":"https://openalex.org/W2037594241","doi":"https://doi.org/10.14778/1687627.1687686","title":"Learning string transformations from examples","display_name":"Learning string transformations from examples","publication_year":2009,"publication_date":"2009-08-01","ids":{"openalex":"https://openalex.org/W2037594241","doi":"https://doi.org/10.14778/1687627.1687686","mag":"2037594241"},"language":"en","primary_location":{"id":"doi:10.14778/1687627.1687686","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687686","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","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/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"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","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"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","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"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026802346"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":8.3318,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.97641362,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"2","issue":"1","first_page":"514","last_page":"525"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9955999851226807,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9947999715805054,"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/string","display_name":"String (physics)","score":0.6941202878952026},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.6911994218826294},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.6383600831031799},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6163557767868042},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6010258793830872},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"Approximate string matching","score":0.5555435419082642},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5297378301620483},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5149991512298584},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.49273279309272766},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4906667470932007},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4899131655693054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.329220712184906},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.3147066831588745},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26766663789749146},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07727062702178955}],"concepts":[{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6941202878952026},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.6911994218826294},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.6383600831031799},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6163557767868042},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6010258793830872},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.5555435419082642},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5297378301620483},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5149991512298584},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.49273279309272766},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4906667470932007},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4899131655693054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.329220712184906},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.3147066831588745},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26766663789749146},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07727062702178955},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.14778/1687627.1687686","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687686","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1010.4841","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1010.4841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Arvind_Arasu/publication/220538475_Learning_String_Transformations_From_Examples/links/004635367c46bb80f6000000.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.151.7904","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.151.7904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.vldb.org/pvldb/2/vldb09-226.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W32508012","https://openalex.org/W1557565723","https://openalex.org/W1567365482","https://openalex.org/W2007682403","https://openalex.org/W2046020929","https://openalex.org/W2057900969","https://openalex.org/W2061820396","https://openalex.org/W2067566391","https://openalex.org/W2072173758","https://openalex.org/W2074409795","https://openalex.org/W2101460669","https://openalex.org/W2108991785","https://openalex.org/W2116493296","https://openalex.org/W2121516976","https://openalex.org/W2143124645","https://openalex.org/W2150546140","https://openalex.org/W2167029568","https://openalex.org/W4248809068"],"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/W2291452290","https://openalex.org/W2037600093","https://openalex.org/W2245915510","https://openalex.org/W2366300241","https://openalex.org/W3145288231"],"abstract_inverted_index":{"\"Robert\"":[0],"and":[1,30],"\"Bob\"":[2],"refer":[3],"to":[4,24,41,45,81,94],"the":[5,61,73,105,123],"same":[6],"first":[7],"name":[8],"but":[9],"are":[10,92],"textually":[11],"far":[12],"apart.":[13],"Traditional":[14],"string":[15,33,83],"similarity":[16],"functions":[17],"do":[18],"not":[19],"allow":[20],"a":[21,39,96,109],"flexible":[22],"way":[23],"account":[25],"for":[26,113],"such":[27,46],"synonyms,":[28],"abbreviations":[29],"aliases.":[31],"Recently,":[32],"transformations":[34,57,65,100],"have":[35],"been":[36],"proposed":[37],"as":[38,60],"mechanism":[40],"make":[42],"matching":[43,79],"robust":[44],"variations.":[47],"However,":[48],"in":[49],"many":[50],"domains,":[51],"identifying":[52],"an":[53,87],"appropriate":[54],"set":[55,98],"of":[56,63,75,78,99,104,125],"is":[58,66],"challenging":[59],"space":[62],"possible":[64],"large.":[67],"In":[68],"this":[69,114],"paper,":[70],"we":[71,91],"investigate":[72],"problem":[74,89],"leveraging":[76],"examples":[77],"strings":[80],"learn":[82,95],"transformations.":[84],"We":[85,107],"formulate":[86],"optimization":[88],"where":[90],"required":[93],"concise":[97],"that":[101],"explain":[102],"most":[103],"differences.":[106],"propose":[108],"greedy":[110],"approximation":[111],"algorithm":[112],"NP-hard":[115],"problem.":[116],"Our":[117],"experiments":[118],"over":[119],"real-life":[120],"data":[121],"illustrate":[122],"benefits":[124],"our":[126],"approach.":[127]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}