{"id":"https://openalex.org/W3093721172","doi":"https://doi.org/10.1145/3340531.3412080","title":"A Comparison of Top-k Threshold Estimation Techniques for Disjunctive Query Processing","display_name":"A Comparison of Top-k Threshold Estimation Techniques for Disjunctive Query Processing","publication_year":2020,"publication_date":"2020-10-19","ids":{"openalex":"https://openalex.org/W3093721172","doi":"https://doi.org/10.1145/3340531.3412080","mag":"3093721172"},"language":"en","primary_location":{"id":"doi:10.1145/3340531.3412080","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340531.3412080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Information & 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/A5004258130","display_name":"Antonio Mallia","orcid":"https://orcid.org/0000-0002-7817-6140"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Antonio Mallia","raw_affiliation_strings":["New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015117459","display_name":"Micha\u0142 Siedlaczek","orcid":"https://orcid.org/0000-0002-9168-0851"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michal Siedlaczek","raw_affiliation_strings":["New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055917672","display_name":"Mengyang Sun","orcid":"https://orcid.org/0000-0003-0638-3295"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyang Sun","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074323303","display_name":"Torsten Suel","orcid":"https://orcid.org/0000-0002-8324-980X"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Torsten Suel","raw_affiliation_strings":["New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5004258130"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":1.5283,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.83607306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2141","last_page":"2144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9991999864578247,"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":0.9907000064849854,"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"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9767000079154968,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7819439172744751},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.6129354238510132},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5310737490653992},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.48222100734710693},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47347748279571533},{"id":"https://openalex.org/keywords/online-aggregation","display_name":"Online aggregation","score":0.4609449803829193},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.45897147059440613},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.43647074699401855},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4263211488723755},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.4196474850177765},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.3535522222518921},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.33944669365882874},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.20060935616493225},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1736416518688202},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13393813371658325},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.09919217228889465}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7819439172744751},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.6129354238510132},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5310737490653992},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.48222100734710693},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47347748279571533},{"id":"https://openalex.org/C24028149","wikidata":"https://www.wikidata.org/wiki/Q7094056","display_name":"Online aggregation","level":5,"score":0.4609449803829193},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.45897147059440613},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.43647074699401855},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4263211488723755},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.4196474850177765},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.3535522222518921},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.33944669365882874},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.20060935616493225},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1736416518688202},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13393813371658325},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.09919217228889465},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3340531.3412080","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340531.3412080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Information & 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":28,"referenced_works":["https://openalex.org/W1495124840","https://openalex.org/W1791987072","https://openalex.org/W1980344365","https://openalex.org/W1982387198","https://openalex.org/W1984918470","https://openalex.org/W2002682102","https://openalex.org/W2029911720","https://openalex.org/W2063694594","https://openalex.org/W2065472179","https://openalex.org/W2093390569","https://openalex.org/W2098294664","https://openalex.org/W2104588805","https://openalex.org/W2115939989","https://openalex.org/W2127899914","https://openalex.org/W2137250554","https://openalex.org/W2154610494","https://openalex.org/W2171144050","https://openalex.org/W2238306519","https://openalex.org/W2303997053","https://openalex.org/W2740256306","https://openalex.org/W2740817677","https://openalex.org/W2799147087","https://openalex.org/W2928680648","https://openalex.org/W2955135504","https://openalex.org/W2986694323","https://openalex.org/W3102704970","https://openalex.org/W4206765718","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3125756434","https://openalex.org/W2096359267","https://openalex.org/W185198413","https://openalex.org/W2034583622","https://openalex.org/W2184296057","https://openalex.org/W2889903446","https://openalex.org/W2150741898","https://openalex.org/W2362460270","https://openalex.org/W4321649654","https://openalex.org/W1793997780"],"abstract_inverted_index":{"In":[0,90],"the":[1,10,15,18],"top-k":[2,126],"threshold":[3],"estimation":[4,108],"problem,":[5],"given":[6],"a":[7,71],"query":[8,37,49,127],"q,":[9],"goal":[11],"is":[12],"to":[13,82,121],"estimate":[14,25],"score":[16,28],"of":[17,26,107,113,124],"result":[19,30],"at":[20],"rank":[21],"k.":[22],"A":[23],"good":[24],"this":[27,91,95],"can":[29],"in":[31,105],"significant":[32],"performance":[33,118],"improvements":[34],"for":[35],"several":[36],"processing":[38,50,128],"scenarios,":[39],"including":[40,63],"selective":[41],"search,":[42],"index":[43],"tiering,":[44],"and":[45,56,70,102,116],"widely":[46],"used":[47],"disjunctive":[48,125],"algorithms":[51],"such":[52],"as":[53],"MaxScore,":[54],"WAND,":[55],"BMW.":[57],"Several":[58],"approaches":[59,101],"have":[60],"been":[61],"proposed,":[62],"parametric":[64],"approaches,":[65],"methods":[66],"using":[67],"random":[68],"sampling,":[69],"recent":[72],"approach":[73],"based":[74],"on":[75],"machine":[76],"learning.":[77],"However,":[78],"previous":[79],"work":[80],"fails":[81],"perform":[83],"any":[84],"experimental":[85],"comparison":[86],"between":[87],"these":[88],"approaches.":[89],"paper,":[92],"we":[93],"address":[94],"issue":[96],"by":[97],"reimplementing":[98],"four":[99],"major":[100],"comparing":[103],"them":[104],"terms":[106],"error,":[109],"running":[110],"time,":[111],"likelihood":[112],"an":[114],"overestimate,":[115],"end-to-end":[117],"when":[119],"applied":[120],"common":[122],"classes":[123],"algorithms.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}