{"id":"https://openalex.org/W2044163187","doi":"https://doi.org/10.1145/2463676.2465313","title":"String similarity measures and joins with synonyms","display_name":"String similarity measures and joins with synonyms","publication_year":2013,"publication_date":"2013-06-22","ids":{"openalex":"https://openalex.org/W2044163187","doi":"https://doi.org/10.1145/2463676.2465313","mag":"2044163187"},"language":"en","primary_location":{"id":"doi:10.1145/2463676.2465313","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2463676.2465313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 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/A5018627557","display_name":"Jiaheng Lu","orcid":"https://orcid.org/0000-0003-2067-454X"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiaheng Lu","raw_affiliation_strings":["School of Information and DEKE, MOE, Renmin University of China, Beijing, China","School of Information and DEKE, MOE, Renmin University of China, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Information and DEKE, MOE, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"School of Information and DEKE, MOE, Renmin University of China, Beijing, China#TAB#","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036384670","display_name":"Chunbin Lin","orcid":"https://orcid.org/0000-0002-7068-9929"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunbin Lin","raw_affiliation_strings":["School of Information and DEKE, MOE, Renmin University of China, Beijing, China","School of Information and DEKE, MOE, Renmin University of China, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Information and DEKE, MOE, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"School of Information and DEKE, MOE, Renmin University of China, Beijing, China#TAB#","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392089","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-8180-2886"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["University of New South Wales, Sydney, Australia","University of New South wales, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"University of New South wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369885","display_name":"Chen Li","orcid":"https://orcid.org/0000-0002-8784-8148"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Li","raw_affiliation_strings":["University of California, Irvine, California, USA","University of California , Irvine, California, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, California, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"University of California , Irvine, California, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101619549","display_name":"Haiyong Wang","orcid":"https://orcid.org/0000-0003-0072-3949"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyong Wang","raw_affiliation_strings":["School of Information and DEKE, MOE, Renmin University of China, Beijing, China","School of Information and DEKE, MOE, Renmin University of China, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Information and DEKE, MOE, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"School of Information and DEKE, MOE, Renmin University of China, Beijing, China#TAB#","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018627557"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":5.975,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.96090033,"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":"373","last_page":"384"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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":0.9975000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.8828830718994141},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.75373774766922},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.693946123123169},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6820008754730225},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"Approximate string matching","score":0.6763798594474792},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.669251024723053},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5599556565284729},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5424526333808899},{"id":"https://openalex.org/keywords/string-kernel","display_name":"String kernel","score":0.5342966914176941},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4394301772117615},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.41566652059555054},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.40209197998046875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3918399214744568},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35357511043548584},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3505855202674866},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06285205483436584},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.05611461400985718}],"concepts":[{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.8828830718994141},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.75373774766922},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.693946123123169},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6820008754730225},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.6763798594474792},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.669251024723053},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5599556565284729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5424526333808899},{"id":"https://openalex.org/C55851704","wikidata":"https://www.wikidata.org/wiki/Q7623983","display_name":"String kernel","level":5,"score":0.5342966914176941},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4394301772117615},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.41566652059555054},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.40209197998046875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3918399214744568},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35357511043548584},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3505855202674866},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06285205483436584},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.05611461400985718},{"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/C160446489","wikidata":"https://www.wikidata.org/wiki/Q7226642","display_name":"Polynomial kernel","level":4,"score":0.0},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2463676.2465313","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2463676.2465313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.352.9880","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.352.9880","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.unsw.edu.au/~weiw/files/SIGMOD13-SimJoinWithRules-Final.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.419.4551","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.419.4551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://datasearch.ruc.edu.cn/paper/SIGMOD 2013.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":42,"referenced_works":["https://openalex.org/W46452414","https://openalex.org/W112827926","https://openalex.org/W1646278814","https://openalex.org/W1785933978","https://openalex.org/W1973001156","https://openalex.org/W1978394996","https://openalex.org/W1988434420","https://openalex.org/W1995437102","https://openalex.org/W2000482994","https://openalex.org/W2025051251","https://openalex.org/W2037594241","https://openalex.org/W2064379477","https://openalex.org/W2065259291","https://openalex.org/W2072173758","https://openalex.org/W2095368471","https://openalex.org/W2096598900","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2099370490","https://openalex.org/W2100548092","https://openalex.org/W2105423800","https://openalex.org/W2107079154","https://openalex.org/W2115214414","https://openalex.org/W2115215982","https://openalex.org/W2117703483","https://openalex.org/W2121269638","https://openalex.org/W2121516976","https://openalex.org/W2127675794","https://openalex.org/W2133627190","https://openalex.org/W2147033904","https://openalex.org/W2150916025","https://openalex.org/W2152565070","https://openalex.org/W2161936973","https://openalex.org/W2162592052","https://openalex.org/W2163993443","https://openalex.org/W2164456230","https://openalex.org/W2167847032","https://openalex.org/W6611201923","https://openalex.org/W6637957267","https://openalex.org/W6674576723","https://openalex.org/W6683401941","https://openalex.org/W6764604475"],"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/W2074064717","https://openalex.org/W2366300241","https://openalex.org/W3145288231"],"abstract_inverted_index":{"A":[0],"string":[1,13,99,111],"similarity":[2,6,34,100],"measure":[3],"quantifies":[4],"the":[5,19,33,67,86,89,108],"between":[7],"two":[8,36],"text":[9],"strings":[10,20,37,64],"for":[11],"approximate":[12],"matching":[14],"or":[15,47],"comparison.":[16],"For":[17,71],"example,":[18,72],"\"Sam\"":[21],"and":[22,104],"\"Samuel\"":[23],"can":[24,65],"be":[25],"considered":[26],"similar.":[27],"Most":[28],"existing":[29,95],"work":[30],"that":[31],"computes":[32],"of":[35,44,54,78,83,88,110],"only":[38],"considers":[39],"syntactic":[40],"similarities,":[41],"e.g.,":[42],"number":[43],"common":[45],"words":[46],"q-grams.":[48],"While":[49],"these":[50],"are":[51,57],"indeed":[52],"indicators":[53],"similarity,":[55],"there":[56],"many":[58],"important":[59],"cases":[60],"where":[61],"syntactically":[62],"different":[63],"represent":[66],"same":[68],"real-world":[69],"object.":[70],"\"Bill\"":[73],"is":[74,91],"a":[75,81],"short":[76],"form":[77],"\"William\".":[79],"Given":[80],"collection":[82],"predefined":[84],"synonyms,":[85],"purpose":[87],"paper":[90],"to":[92,97],"explore":[93],"such":[94],"knowledge":[96],"evaluate":[98],"measures":[101],"more":[102],"effectively":[103],"efficiently,":[105],"thereby":[106],"boosting":[107],"quality":[109],"matching.":[112]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}