{"id":"https://openalex.org/W2130825214","doi":"https://doi.org/10.1109/icde.2011.5767856","title":"Answering approximate string queries on large data sets using external memory","display_name":"Answering approximate string queries on large data sets using external memory","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2130825214","doi":"https://doi.org/10.1109/icde.2011.5767856","mag":"2130825214"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2011.5767856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2011.5767856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE 27th International Conference on Data Engineering","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/A5039486762","display_name":"Alexander Behm","orcid":null},"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":true,"raw_author_name":"Alexander Behm","raw_affiliation_strings":["Department of Computer Science, University of California, Irvine, USA","Deptarment of Computer Science, University of California, Irvine, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"Deptarment of Computer Science, University of California, Irvine, USA#TAB#","institution_ids":["https://openalex.org/I204250578"]}]},{"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":["Department of Computer Science, University of California, Irvine, USA","Deptarment of Computer Science, University of California, Irvine, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"Deptarment of Computer Science, University of California, Irvine, USA#TAB#","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011512061","display_name":"Michael J. Carey","orcid":"https://orcid.org/0000-0003-1561-4059"},"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":"Michael J. Carey","raw_affiliation_strings":["Department of Computer Science, University of California, Irvine, USA","Deptarment of Computer Science, University of California, Irvine, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"Deptarment of Computer Science, University of California, Irvine, USA#TAB#","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5039486762"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":null,"apc_paid":null,"fwci":5.7361,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.96099453,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994999766349792,"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":0.9994999766349792,"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/T11106","display_name":"Data Management and Algorithms","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8578581809997559},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6892494559288025},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.6600497364997864},{"id":"https://openalex.org/keywords/auxiliary-memory","display_name":"Auxiliary memory","score":0.6201193928718567},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5967737436294556},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5364782214164734},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.4712762236595154},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4707534909248352},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4675993323326111},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.43833011388778687},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40003639459609985},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.23368653655052185},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09014132618904114},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08963149785995483}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8578581809997559},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6892494559288025},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.6600497364997864},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.6201193928718567},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5967737436294556},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5364782214164734},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.4712762236595154},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4707534909248352},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4675993323326111},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.43833011388778687},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40003639459609985},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.23368653655052185},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09014132618904114},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08963149785995483},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icde.2011.5767856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2011.5767856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE 27th International Conference on Data Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.221.2592","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.221.2592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ics.uci.edu/%7Echenli/pub/2011-icde.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":23,"referenced_works":["https://openalex.org/W1540616176","https://openalex.org/W1974995373","https://openalex.org/W2001496424","https://openalex.org/W2032327675","https://openalex.org/W2043481183","https://openalex.org/W2049804814","https://openalex.org/W2096598900","https://openalex.org/W2097776316","https://openalex.org/W2107293766","https://openalex.org/W2108235229","https://openalex.org/W2121516976","https://openalex.org/W2127675794","https://openalex.org/W2137339254","https://openalex.org/W2138662031","https://openalex.org/W2140453381","https://openalex.org/W2142009257","https://openalex.org/W2148148676","https://openalex.org/W2150916025","https://openalex.org/W2161936973","https://openalex.org/W2167847032","https://openalex.org/W6632287593","https://openalex.org/W6674576723","https://openalex.org/W6683401941"],"related_works":["https://openalex.org/W4250826546","https://openalex.org/W1988679864","https://openalex.org/W2072336782","https://openalex.org/W49772301","https://openalex.org/W2163073686","https://openalex.org/W2041762692","https://openalex.org/W144222265","https://openalex.org/W2567477113","https://openalex.org/W2088116875","https://openalex.org/W2097224604"],"abstract_inverted_index":{"An":[0],"approximate":[1],"string":[2],"query":[3,19],"is":[4,24],"to":[5,16,61,92,99,139],"find":[6],"from":[7],"a":[8,17,67,84,111,140,160],"collection":[9],"of":[10,75,120],"strings":[11],"those":[12],"that":[13,115,134,148],"are":[14],"similar":[15],"given":[18],"string.":[20],"Answering":[21],"such":[22,29,64],"queries":[23,41,65,94,153],"important":[25],"in":[26,40,66],"many":[27],"applications":[28],"as":[30,42,44],"data":[31,77],"cleaning":[32],"and":[33,78,95,124,147],"record":[34],"linkage,":[35],"where":[36],"errors":[37],"could":[38],"occur":[39],"well":[43,146],"the":[45,73,117],"data.":[46],"Many":[47],"existing":[48,137],"algorithms":[49,138],"have":[50],"focused":[51],"on":[52,80,129],"in-memory":[53],"indexes.":[54],"In":[55],"this":[56],"paper":[57],"we":[58,96,109],"investigate":[59],"how":[60,98],"efficiently":[62],"answer":[63,93,107,152],"disk-based":[68,141],"setting,":[69],"by":[70],"systematically":[71],"studying":[72],"effects":[74],"storing":[76],"indexes":[79],"disk.":[81],"We":[82],"devise":[83],"novel":[85],"physical":[86],"layout":[87],"for":[88],"an":[89],"inverted":[90,126],"index":[91],"study":[97],"construct":[100],"it":[101],"with":[102],"limited":[103],"buffer":[104],"space.":[105],"To":[106],"queries,":[108],"develop":[110],"cost-based,":[112],"adaptive":[113],"algorithm":[114],"balances":[116],"I/O":[118],"costs":[119],"retrieving":[121],"candidate":[122],"matches":[123],"accessing":[125],"lists.":[127],"Experiments":[128],"large,":[130],"real":[131],"datasets":[132],"verify":[133],"simply":[135],"adapting":[136],"setting":[142],"does":[143],"not":[144],"work":[145],"our":[149,156],"new":[150],"techniques":[151],"efficiently.":[154],"Further,":[155],"solutions":[157],"significantly":[158],"outperform":[159],"recent":[161],"tree-based":[162],"index,":[163],"BED-tree.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}