{"id":"https://openalex.org/W1970807116","doi":"https://doi.org/10.1145/1871437.1871714","title":"CasJoin","display_name":"CasJoin","publication_year":2010,"publication_date":"2010-10-26","ids":{"openalex":"https://openalex.org/W1970807116","doi":"https://doi.org/10.1145/1871437.1871714","mag":"1970807116"},"language":"en","primary_location":{"id":"doi:10.1145/1871437.1871714","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","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/A5109175228","display_name":"Xiaoxun Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoxun Zhang","raw_affiliation_strings":["IBM Research - China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"IBM Research - China, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101725207","display_name":"Zhili Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhili Guo","raw_affiliation_strings":["IBM Research - China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"IBM Research - China, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001909797","display_name":"Honglei Guo","orcid":"https://orcid.org/0000-0002-1485-1987"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honglei Guo","raw_affiliation_strings":["IBM Research - China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"IBM Research - China, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110390049","display_name":"Huijia Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huijia Zhu","raw_affiliation_strings":["IBM Research - China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"IBM Research - China, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010426520","display_name":"Zhong Su","orcid":"https://orcid.org/0000-0003-2303-9787"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Su","raw_affiliation_strings":["IBM Research - China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"IBM Research - China, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5109175228"],"corresponding_institution_ids":["https://openalex.org/I4210126794"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11798273,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1725","last_page":"1728"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994000196456909,"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":0.9990000128746033,"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/speedup","display_name":"Speedup","score":0.8880100250244141},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.827521800994873},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.801522433757782},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.7547732591629028},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5993055701255798},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.5084263682365417},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.47752654552459717},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4465842843055725},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3763410747051239},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3413764238357544},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3217448592185974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3208358585834503},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.26662272214889526},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10688215494155884},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07910433411598206}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8880100250244141},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.827521800994873},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.801522433757782},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.7547732591629028},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5993055701255798},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.5084263682365417},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.47752654552459717},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4465842843055725},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3763410747051239},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3413764238357544},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3217448592185974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3208358585834503},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.26662272214889526},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10688215494155884},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07910433411598206},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1871437.1871714","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1604437383","https://openalex.org/W2096598900","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2104955141","https://openalex.org/W2112261435","https://openalex.org/W2121516976","https://openalex.org/W2127675794","https://openalex.org/W3097096317","https://openalex.org/W6674576723"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2088925915","https://openalex.org/W2027972911","https://openalex.org/W2382891957","https://openalex.org/W2157978810"],"abstract_inverted_index":{"We":[0,101,145],"are":[1,137],"concerned":[2],"with":[3],"the":[4,13,109,119,160],"problem":[5,28],"of":[6,9,20,53,64,85,111,122,133,170,181],"similarity":[7,55],"joins":[8,71],"text":[10,70],"data,":[11],"where":[12,76],"task":[14],"is":[15,42,95,128],"to":[16,43,98,107,118,159,185],"find":[17],"all":[18],"pairs":[19,47,87],"documents":[21],"above":[22],"an":[23,32,62],"expected":[24],"similarity.":[25],"Such":[26],"a":[27,66,73,77,82,104,115,126,131,150,167,178],"often":[29],"serves":[30],"as":[31,48,50,99,173,175],"indispensable":[33],"step":[34],"in":[35,69,89],"many":[36,49],"web":[37,152],"applications.":[38],"A":[39],"crucial":[40],"issue":[41],"preclude":[44],"unnecessary":[45],"candidate":[46],"possible":[51],"ahead":[52],"expensive":[54],"evaluation.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60],"initiate":[61],"idea":[63],"adopting":[65],"cascade":[67,143],"structure":[68],"for":[72,142],"large":[74],"speedup,":[75],"latter":[78],"stage":[79,110],"can":[80,165],"exclude":[81],"considerable":[83],"number":[84],"invalid":[86],"survived":[88],"former":[90],"stages.":[91],"The":[92],"proposed":[93],"algorithm":[94],"shortly":[96],"referred":[97],"CasJoin.":[100],"further":[102],"adopt":[103],"prefix":[105,162],"filter":[106],"build":[108],"CasJoin":[112,148,164],"by":[113,140,172,183],"introducing":[114],"novel":[116],"vision":[117],"dynamic":[120],"generation":[121],"document":[123],"vector.":[124],"Specifically,":[125],"vector":[127],"partitioned":[129],"into":[130],"chain":[132],"multiple":[134],"prefixes":[135],"that":[136],"appended":[138],"one":[139,141],"joining.":[144],"evaluate":[146],"our":[147],"on":[149],"typical":[151],"corpus,":[153],"ODP.":[154],"Experiments":[155],"indicate":[156],"that,":[157],"comparing":[158],"state-of-the-art":[161],"algorithms,":[163],"achieve":[166],"drastic":[168],"reduction":[169],"candidates":[171],"much":[174],"98.15%":[176],"and":[177],"dramatic":[179],"speedup":[180],"joining":[182],"up":[184],"13.34x.":[186]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}