{"id":"https://openalex.org/W2399368377","doi":"https://doi.org/10.1007/978-3-319-25159-2_24","title":"String Similarity Join with Different Thresholds","display_name":"String Similarity Join with Different Thresholds","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2399368377","doi":"https://doi.org/10.1007/978-3-319-25159-2_24","mag":"2399368377"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-25159-2_24","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"book-chapter","type_crossref":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/978-3-319-25159-2_24","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039663122","display_name":"Chuitian Rong","orcid":"https://orcid.org/0000-0003-2949-3892"},"institutions":[{"id":"https://openalex.org/I198091727","display_name":"Tianjin Polytechnic University","ror":"https://ror.org/00xsr9m91","country_code":"CN","type":"education","lineage":["https://openalex.org/I198091727"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chuitian Rong","raw_affiliation_strings":["School of Computer Science and Software Engineering, Tianjin Polytechnic University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Software Engineering, Tianjin Polytechnic University, Tianjin, China","institution_ids":["https://openalex.org/I198091727"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031731872","display_name":"Xiangling Zhang","orcid":null},"institutions":[],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangling Zhang","raw_affiliation_strings":["Key Labs of Data Engineering and Knowledge Engineering, MOE, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Labs of Data Engineering and Knowledge Engineering, MOE, Beijing, China","institution_ids":[]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5039663122"],"corresponding_institution_ids":["https://openalex.org/I198091727"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392,"provenance":"doaj"},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392,"provenance":"doaj"},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":66},"biblio":{"volume":null,"issue":null,"first_page":"260","last_page":"271"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality Assessment and Improvement","score":0.9999,"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 Assessment and Improvement","score":0.9999,"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 Extraction and Crawling Techniques","score":0.9977,"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":"Natural Language Processing","score":0.9823,"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/similarity","display_name":"Similarity (geometry)","score":0.8174994},{"id":"https://openalex.org/keywords/string-similarity","display_name":"String Similarity","score":0.649145},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.5593359},{"id":"https://openalex.org/keywords/duplicate-detection","display_name":"Duplicate Detection","score":0.51886},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic Similarity","score":0.518368},{"id":"https://openalex.org/keywords/similitude","display_name":"Similitude","score":0.5037276},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.48669058},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.45084974}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.8937104},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.8174994},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.8114816},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.75069326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7337426},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.5593359},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.5037276},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.50217557},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.48669058},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.45084974},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42332485},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35406417},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.34531182},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32454455},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18481374},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.120394856},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06759563},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.06641084},{"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-25159-2_24","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-25159-2_24","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":20,"referenced_works":["https://openalex.org/W1995099886","https://openalex.org/W2012964802","https://openalex.org/W2024770506","https://openalex.org/W2044163187","https://openalex.org/W2046020929","https://openalex.org/W2073167797","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2108991785","https://openalex.org/W2121269638","https://openalex.org/W2121516976","https://openalex.org/W2127675794","https://openalex.org/W2131846894","https://openalex.org/W2150698190","https://openalex.org/W2161936973","https://openalex.org/W2166400748","https://openalex.org/W2621280964","https://openalex.org/W4254788633","https://openalex.org/W4302802341","https://openalex.org/W46452414"],"related_works":["https://openalex.org/W52396946","https://openalex.org/W4386026606","https://openalex.org/W2952544458","https://openalex.org/W2405436873","https://openalex.org/W2399644331","https://openalex.org/W2187092961","https://openalex.org/W2131677984","https://openalex.org/W1998140328","https://openalex.org/W1973578339","https://openalex.org/W1824878879"],"abstract_inverted_index":{"String":[0],"similarity":[1,31,70,74,84,89,122],"join":[2],"is":[3,49,101],"an":[4],"essential":[5],"operation":[6],"of":[7,59],"many":[8,45],"applications":[9],"that":[10,38,115],"need":[11],"to":[12,51,55,81,105],"find":[13],"all":[14],"similar":[15],"string":[16,41,69],"pairs":[17,42],"from":[18],"given":[19],"two":[20],"collections.":[21],"The":[22],"existing":[23],"approaches":[24],"are":[25],"using":[26],"the":[27,39,88,102,107],"uniform":[28],"and":[29,92],"predefined":[30],"thresholds.":[32],"While":[33],"in":[34,76],"real":[35],"applications,":[36],"regarding":[37],"longer":[40],"typically":[43],"tolerate":[44],"more":[46],"typos,":[47],"it":[48,100],"necessary":[50],"apply":[52],"variable":[53],"thresholds":[54,75,123],"different":[56,73,83,121],"strings":[57],"instead":[58],"a":[60,66],"constant":[61],"one.":[62],"Therefore,":[63],"we":[64,86],"proposed":[65],"solution":[67,117],"for":[68],"joins":[71],"with":[72,120],"one":[77],"procedure.":[78],"In":[79],"order":[80],"support":[82],"thresholds,":[85],"devised":[87],"aware":[90],"index":[91,93],"probing":[94],"technique.":[95],"To":[96],"our":[97,116],"best":[98],"knowledge,":[99],"first":[103],"work":[104],"address":[106],"problem.":[108],"Experimental":[109],"results":[110],"on":[111],"real-world":[112],"datasets":[113],"show":[114],"can":[118],"tackle":[119],"efficiently.":[124]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2399368377","counts_by_year":[],"updated_date":"2024-09-17T05:55:34.797492","created_date":"2016-06-24"}