{"id":"https://openalex.org/W2024651132","doi":"https://doi.org/10.1145/2818177","title":"Boosting the Quality of Approximate String Matching by Synonyms","display_name":"Boosting the Quality of Approximate String Matching by Synonyms","publication_year":2015,"publication_date":"2015-10-23","ids":{"openalex":"https://openalex.org/W2024651132","doi":"https://doi.org/10.1145/2818177","mag":"2024651132"},"language":"en","primary_location":{"id":"doi:10.1145/2818177","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2818177","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"ACM Transactions on Database Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10138/158483","any_repository_has_fulltext":true},"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"]},{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["CN","FI"],"is_corresponding":true,"raw_author_name":"Jiaheng Lu","raw_affiliation_strings":["Renmin University of China and University of Helsinki, Finland"],"affiliations":[{"raw_affiliation_string":"Renmin University of China and University of Helsinki, Finland","institution_ids":["https://openalex.org/I78988378","https://openalex.org/I133731052"]}]},{"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/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunbin Lin","raw_affiliation_strings":["University of California, San Diego, La Jolla, CA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, La Jolla, CA","institution_ids":["https://openalex.org/I36258959"]}]},{"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, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South Wales, 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, CA"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, CA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010903591","display_name":"Xiaokui Xiao","orcid":"https://orcid.org/0000-0003-0914-4580"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiaokui Xiao","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018627557"],"corresponding_institution_ids":["https://openalex.org/I133731052","https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":1.4238302,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.86264657,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"40","issue":"3","first_page":"1","last_page":"42"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9973999857902527,"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":0.9943000078201294,"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/computer-science","display_name":"Computer science","score":0.7855785489082336},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.7808862924575806},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.7017489671707153},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6286725997924805},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.6265549659729004},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"Approximate string matching","score":0.6238977313041687},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5664174556732178},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5604121685028076},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5250102281570435},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4289284646511078},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.42717409133911133},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.40436410903930664},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.3993302583694458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3127962350845337},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16837939620018005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7855785489082336},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.7808862924575806},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.7017489671707153},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6286725997924805},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.6265549659729004},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.6238977313041687},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5664174556732178},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5604121685028076},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5250102281570435},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4289284646511078},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.42717409133911133},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40436410903930664},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.3993302583694458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3127962350845337},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16837939620018005},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"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:10.1145/2818177","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2818177","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"ACM Transactions on Database Systems","raw_type":"journal-article"},{"id":"pmh:oai:helda.helsinki.fi:10138/158483","is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/158483","pdf_url":"http://hdl.handle.net/10138/158483","source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-157771","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-157771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:helda.helsinki.fi:10138/158483","is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/158483","pdf_url":"http://hdl.handle.net/10138/158483","source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310086","display_name":"Helsingin Yliopisto","ror":"https://ror.org/040af2s02"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2024651132.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W46452414","https://openalex.org/W1527957260","https://openalex.org/W1646278814","https://openalex.org/W1785933978","https://openalex.org/W1821184416","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/W2031250218","https://openalex.org/W2037594241","https://openalex.org/W2044163187","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/W2100548092","https://openalex.org/W2105423800","https://openalex.org/W2107079154","https://openalex.org/W2115215982","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/W2163550466","https://openalex.org/W2163993443","https://openalex.org/W2164456230","https://openalex.org/W2167847032","https://openalex.org/W4389615664"],"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/W2178786736"],"abstract_inverted_index":{"A":[0],"string-similarity":[1],"measure":[2,141],"quantifies":[3],"the":[4,18,34,70,98,112,126,177,188,227,235,242],"similarity":[5,35,113,120,154],"between":[6,114],"two":[7,37,115,160],"text":[8],"strings":[9,19,38,67,116],"for":[10,43,153],"approximate":[11,129],"string":[12,130,142],"matching":[13],"or":[14,49],"comparison.":[15],"For":[16,74],"example,":[17,44,75],"\u201cSam\u201d":[20],"and":[21,83,117,122,156,165,170,212,223,244],"\u201cSamuel\u201d":[22],"can":[23,68,87],"be":[24,27,88],"considered":[25],"to":[26,104,109,140,175,186,192],"similar.":[28],"Most":[29],"existing":[30,107],"work":[31],"that":[32],"computes":[33],"of":[36,46,58,81,95,100,128,179,190,197,234,246],"only":[39,209],"considers":[40],"syntactic":[41],"similarities,":[42],"number":[45],"common":[47],"words":[48],"q":[50],"-grams.":[51],"While":[52],"this":[53,101],"is":[54,77,103],"indeed":[55],"an":[56,137,184,194],"indicator":[57],"similarity,":[59],"there":[60],"are":[61],"many":[62],"important":[63],"cases":[64],"where":[65],"syntactically-different":[66],"represent":[69],"same":[71],"real-world":[72],"object.":[73],"\u201cBill\u201d":[76],"a":[78,93,231],"short":[79],"form":[80],"\u201cWilliam,\u201d":[82],"\u201cDatabase":[84],"Management":[85],"Systems\u201d":[86],"abbreviated":[89],"as":[90],"\u201cDBMS.\u201d":[91],"Given":[92],"collection":[94],"predefined":[96],"synonyms,":[97],"purpose":[99],"article":[102],"explore":[105],"such":[106],"knowledge":[108],"effectively":[110],"evaluate":[111],"efficiently":[118,144],"perform":[119],"searches":[121,155],"joins,":[123],"thereby":[124],"boosting":[125],"quality":[127],"matching.":[131],"In":[132,173],"particular,":[133],"we":[134,182],"first":[135],"present":[136],"expansion-based":[138],"framework":[139],"similarities":[143],"while":[145,207],"considering":[146],"synonyms.":[147],"We":[148],"then":[149],"study":[150,233],"efficient":[151],"algorithms":[152,236],"joins":[157],"by":[158],"proposing":[159],"novel":[161],"indexes,":[162],"called":[163],"SI-trees":[164],"QP-trees,":[166],"which":[167],"combine":[168],"signature-filtering":[169],"length-filtering":[171],"strategies.":[172],"order":[174],"improve":[176],"efficiency":[178,245],"our":[180,217,247],"algorithms,":[181],"develop":[183],"estimator":[185,201],"estimate":[187],"size":[189],"candidates":[191],"enable":[193],"online":[195],"selection":[196],"signature":[198],"filters.":[199],"This":[200],"provides":[202],"strong":[203],"low-error,":[204],"high-confidence":[205],"guarantees":[206],"requiring":[208],"logarithmic":[210],"space":[211],"time":[213],"costs,":[214],"thus":[215],"making":[216],"method":[218],"attractive":[219],"both":[220],"in":[221,224],"theory":[222],"practice.":[225],"Finally,":[226],"experimental":[228],"results":[229],"from":[230],"comprehensive":[232],"with":[237],"three":[238],"real":[239],"datasets":[240],"verify":[241],"effectiveness":[243],"approaches.":[248]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}