{"id":"https://openalex.org/W3129744650","doi":"https://doi.org/10.14778/3436905.3436907","title":"Astrid","display_name":"Astrid","publication_year":2020,"publication_date":"2020-12-01","ids":{"openalex":"https://openalex.org/W3129744650","doi":"https://doi.org/10.14778/3436905.3436907","mag":"3129744650"},"language":"en","primary_location":{"id":"doi:10.14778/3436905.3436907","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3436905.3436907","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5046581906","display_name":"Suraj Shetiya","orcid":"https://orcid.org/0000-0001-9166-2365"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suraj Shetiya","raw_affiliation_strings":["UT Arlington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UT Arlington","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066004392","display_name":"Saravanan Thirumuruganathan","orcid":"https://orcid.org/0000-0002-1517-480X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saravanan Thirumuruganathan","raw_affiliation_strings":["QCRI, HBKU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"QCRI, HBKU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035257754","display_name":"Nick Koudas","orcid":"https://orcid.org/0000-0001-5648-0638"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Nick Koudas","raw_affiliation_strings":["University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002203026","display_name":"Gautam Das","orcid":"https://orcid.org/0000-0002-4627-9065"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gautam Das","raw_affiliation_strings":["UT Arlington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UT Arlington","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4298,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.89554543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"14","issue":"4","first_page":"471","last_page":"484"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9990000128746033,"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":0.9990000128746033,"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/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9966999888420105,"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/substring","display_name":"Substring","score":0.9314334392547607},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7913480997085571},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.6115233302116394},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5519697666168213},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5049512982368469},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.47678330540657043},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.4599115252494812},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.4332706332206726},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.421177476644516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.388715922832489},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.344267338514328},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.28222787380218506},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.2581816613674164},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12307950854301453}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.9314334392547607},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7913480997085571},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.6115233302116394},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5519697666168213},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5049512982368469},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.47678330540657043},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.4599115252494812},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.4332706332206726},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.421177476644516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.388715922832489},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.344267338514328},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.28222787380218506},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2581816613674164},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12307950854301453},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3436905.3436907","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3436905.3436907","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W581956982","https://openalex.org/W1565231908","https://openalex.org/W1578664299","https://openalex.org/W1822348499","https://openalex.org/W1924770834","https://openalex.org/W1947403449","https://openalex.org/W1975517671","https://openalex.org/W1984057771","https://openalex.org/W1984629602","https://openalex.org/W1990061958","https://openalex.org/W1993831977","https://openalex.org/W2005945380","https://openalex.org/W2021850646","https://openalex.org/W2041851430","https://openalex.org/W2053075747","https://openalex.org/W2064675550","https://openalex.org/W2075833184","https://openalex.org/W2095705004","https://openalex.org/W2096733369","https://openalex.org/W2097710895","https://openalex.org/W2119057313","https://openalex.org/W2120108467","https://openalex.org/W2123020735","https://openalex.org/W2136716899","https://openalex.org/W2138621090","https://openalex.org/W2144661390","https://openalex.org/W2147440220","https://openalex.org/W2151310484","https://openalex.org/W2154851992","https://openalex.org/W2158195707","https://openalex.org/W2162481186","https://openalex.org/W2167439683","https://openalex.org/W2168865746","https://openalex.org/W2171903035","https://openalex.org/W2396309311","https://openalex.org/W2396635388","https://openalex.org/W2579528885","https://openalex.org/W2585664214","https://openalex.org/W2598634450","https://openalex.org/W2766026698","https://openalex.org/W2790625403","https://openalex.org/W2802941148","https://openalex.org/W2808009442","https://openalex.org/W2894568782","https://openalex.org/W2913631065","https://openalex.org/W2922602266","https://openalex.org/W2950096404","https://openalex.org/W2950316186","https://openalex.org/W2950577311","https://openalex.org/W2955798121","https://openalex.org/W2957204582","https://openalex.org/W2962771342","https://openalex.org/W2962868088","https://openalex.org/W2963350250","https://openalex.org/W2963389687","https://openalex.org/W2963775347","https://openalex.org/W2970148517","https://openalex.org/W2971681342","https://openalex.org/W2981972129","https://openalex.org/W2982231843","https://openalex.org/W2991530444","https://openalex.org/W2998704965","https://openalex.org/W3003533349","https://openalex.org/W3013447829","https://openalex.org/W3021702690","https://openalex.org/W3030994385","https://openalex.org/W3099158806","https://openalex.org/W3099273181","https://openalex.org/W3103177583","https://openalex.org/W3104097132","https://openalex.org/W3124277639","https://openalex.org/W4230112007","https://openalex.org/W4240302460","https://openalex.org/W4241858315","https://openalex.org/W4246006899","https://openalex.org/W4246225718","https://openalex.org/W4254407475","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2022951409","https://openalex.org/W3196825089","https://openalex.org/W4368367671","https://openalex.org/W3022344494","https://openalex.org/W2070949798","https://openalex.org/W2063556310","https://openalex.org/W4240792180","https://openalex.org/W2738126475","https://openalex.org/W2888404656","https://openalex.org/W2566668411"],"abstract_inverted_index":{"Accurate":[0],"selectivity":[1,48,119,150,194],"estimation":[2,49,120],"for":[3,110,117,175,193,200,205,226,241],"string":[4,118],"predicates":[5],"is":[6,99,106,143,177,208],"a":[7,32,95,107,115,236],"long-standing":[8],"research":[9],"challenge":[10],"in":[11,61],"databases.":[12],"Supporting":[13],"pattern":[14,230],"matching":[15,231],"on":[16],"strings":[17,89,154],"(such":[18],"as":[19,44,84],"prefix,":[20],"substring,":[21,146],"and":[22,90,126,147,149,157,165,238,254],"suffix)":[23,148],"makes":[24],"this":[25,54,98],"problem":[26],"much":[27],"more":[28],"challenging,":[29],"thereby":[30],"necessitating":[31],"dedicated":[33],"study.":[34],"Traditional":[35],"approaches":[36,76,259],"often":[37],"build":[38],"pruned":[39],"summary":[40],"data":[41],"structures":[42],"such":[43,83],"tries":[45],"followed":[46],"by":[47,67],"using":[50],"statistical":[51],"correlations.":[52],"However,":[53],"produces":[55],"insufficiently":[56],"accurate":[57],"cardinality":[58],"estimates":[59],"resulting":[60],"the":[62,68,88,173,212,216,243],"selection":[63],"of":[64,215,229],"sub-optimal":[65],"plans":[66],"query":[69],"optimizer.":[70],"Recently":[71],"proposed":[72,258],"deep":[73,127],"learning":[74,128],"based":[75,129],"leverage":[77],"techniques":[78],"from":[79,124],"natural":[80],"language":[81,188,218],"processing":[82],"embeddings":[85],"to":[86,93,179],"encode":[87],"use":[91],"it":[92,222],"train":[94],"model.":[96],"While":[97,196],"an":[100,139],"improvement":[101],"over":[102,251],"traditional":[103,125],"approaches,":[104],"there":[105],"large":[108],"scope":[109],"improvement.":[111],"We":[112,131,210,233,247],"propose":[113,138,235],"Astrid,":[114],"framework":[116],"that":[121,142,172,221,256],"synthesizes":[122],"ideas":[123],"approaches.":[130],"make":[132],"two":[133],"complementary":[134],"contributions.":[135],"First,":[136],"we":[137,184],"embedding":[140,174],"algorithm":[141,240],"query-type":[144],"(prefix,":[145],"aware.":[151],"Consider":[152],"three":[153],"'ab',":[155],"'abc'":[156,180],"'abd'":[158],"whose":[159],"prefix":[160,201],"frequencies":[161],"are":[162],"1000,":[163],"800":[164],"100":[166],"respectively.":[167],"Our":[168],"approach":[169],"would":[170],"ensure":[171],"'ab'":[176],"closer":[178],"than":[181],"'abd'.":[182],"Second,":[183],"describe":[185],"how":[186],"neural":[187,217],"models":[189],"could":[190,223],"be":[191,224],"used":[192,225],"estimation.":[195],"they":[197],"work":[198],"well":[199],"queries,":[202],"their":[203],"performance":[204],"substring":[206],"queries":[207],"sub-optimal.":[209],"modify":[211],"objective":[213,245],"function":[214],"model":[219],"so":[220],"estimating":[227],"selectivities":[228],"queries.":[232],"also":[234],"novel":[237],"efficient":[239],"optimizing":[242],"new":[244],"function.":[246],"conduct":[248],"extensive":[249],"experiments":[250],"benchmark":[252],"datasets":[253],"show":[255],"our":[257],"achieve":[260],"state-of-the-art":[261],"results.":[262]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2021-03-01T00:00:00"}