{"id":"https://openalex.org/W2112276485","doi":"https://doi.org/10.1145/1007568.1007655","title":"When one sample is not enough","display_name":"When one sample is not enough","publication_year":2004,"publication_date":"2004-06-13","ids":{"openalex":"https://openalex.org/W2112276485","doi":"https://doi.org/10.1145/1007568.1007655","mag":"2112276485"},"language":"en","primary_location":{"id":"doi:10.1145/1007568.1007655","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007568.1007655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 ACM SIGMOD international conference on Management of data","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/A5010731709","display_name":"Panagiotis G. Ipeirotis","orcid":"https://orcid.org/0000-0002-2966-7402"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Panagiotis G. Ipeirotis","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080063580","display_name":"Luis Gravano","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luis Gravano","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010731709"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":7.9811,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.97284167,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"767","last_page":"778"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9959999918937683,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9959999918937683,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9958000183105469,"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/T11106","display_name":"Data Management and Algorithms","score":0.9922999739646912,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8228287696838379},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6560897827148438},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6389265656471252},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5979910492897034},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5514187216758728},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5365794897079468},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5257114768028259},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.4707147479057312},{"id":"https://openalex.org/keywords/zipfs-law","display_name":"Zipf's law","score":0.4557461738586426},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44110867381095886},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.43630608916282654},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4149048924446106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19112133979797363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8228287696838379},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6560897827148438},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6389265656471252},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5979910492897034},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5514187216758728},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5365794897079468},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5257114768028259},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.4707147479057312},{"id":"https://openalex.org/C125932096","wikidata":"https://www.wikidata.org/wiki/Q205472","display_name":"Zipf's law","level":2,"score":0.4557461738586426},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44110867381095886},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.43630608916282654},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4149048924446106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19112133979797363},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1007568.1007655","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007568.1007655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.550000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1523949738","https://openalex.org/W1529740232","https://openalex.org/W1541635151","https://openalex.org/W1544729927","https://openalex.org/W1574633138","https://openalex.org/W1585303489","https://openalex.org/W1956559956","https://openalex.org/W1964653195","https://openalex.org/W1986828474","https://openalex.org/W1990388042","https://openalex.org/W1992053235","https://openalex.org/W2002682102","https://openalex.org/W2012426233","https://openalex.org/W2016892599","https://openalex.org/W2021986193","https://openalex.org/W2023657004","https://openalex.org/W2049633694","https://openalex.org/W2059344928","https://openalex.org/W2061973112","https://openalex.org/W2078206416","https://openalex.org/W2079229534","https://openalex.org/W2086253379","https://openalex.org/W2090805977","https://openalex.org/W2097359597","https://openalex.org/W2109895155","https://openalex.org/W2112492518","https://openalex.org/W2116341550","https://openalex.org/W2131006463","https://openalex.org/W2137845970","https://openalex.org/W2141527751","https://openalex.org/W2160080653","https://openalex.org/W2169044456","https://openalex.org/W2172145850","https://openalex.org/W2325227998","https://openalex.org/W4247346926","https://openalex.org/W4253769013","https://openalex.org/W4255459561","https://openalex.org/W4285719527","https://openalex.org/W6640862754","https://openalex.org/W6680807580","https://openalex.org/W6766120893","https://openalex.org/W6902931378"],"related_works":["https://openalex.org/W3123832408","https://openalex.org/W2137719806","https://openalex.org/W2744330362","https://openalex.org/W17155033","https://openalex.org/W2096748633","https://openalex.org/W2963431268","https://openalex.org/W3131094596","https://openalex.org/W2146223937","https://openalex.org/W2063584014","https://openalex.org/W3207760230"],"abstract_inverted_index":{"Database":[0],"selection":[1,17,88,207,243],"is":[2],"an":[3,41],"important":[4],"step":[5],"when":[6],"searching":[7],"over":[8,174,182],"large":[9,71],"numbers":[10],"of":[11,23,45,101,124,145,152,156],"distributed":[12],"text":[13,47],"databases.":[14,33],"The":[15],"database":[16,25,48,72,87,206,242,255],"task":[18],"relies":[19],"on":[20,107,224],"statistical":[21],"summaries":[22,64,82,123,190],"the":[24,86,99,108,120,146,150,166,187,230],"contents,":[26],"which":[27,222],"are":[28,191],"not":[29],"typically":[30],"exported":[31],"by":[32],"Previous":[34],"research":[35],"has":[36,159],"developed":[37],"algorithms":[38,208],"for":[39,68,91,163,217],"constructing":[40],"approximate":[42,102,121],"content":[43,63,81,103,122,167,189],"summary":[44,168],"a":[46,50,139,218,248],"from":[49],"small":[51],"document":[52,164],"sample":[53],"extracted":[54],"via":[55],"querying.":[56],"Unfortunately,":[57],"Zipf's":[58],"law":[59],"practically":[60],"guarantees":[61],"that":[62,110,158,186,235,253],"built":[65],"this":[66],"way":[67],"any":[69],"relatively":[70],"will":[73],"fail":[74],"to":[75,115,203,209,214],"cover":[76],"many":[77],"low-frequency":[78],"words.":[79,96],"Incomplete":[80],"might":[83],"negatively":[84],"affect":[85],"process,":[89],"especially":[90],"short":[92],"queries":[93],"with":[94],"infrequent":[95],"To":[97],"improve":[98],"coverage":[100],"summaries,":[104],"we":[105,137],"build":[106],"observation":[109],"topically":[111,125],"similar":[112],"databases":[113,127,147,178],"tend":[114],"have":[116],"related":[117,126],"vocabularies.":[118],"Therefore,":[119],"can":[128],"complement":[129],"each":[130],"other":[131],"and":[132,148,229,245],"increase":[133],"their":[134,196],"coverage.":[135],"Specifically,":[136],"exploit":[138],"(given":[140],"or":[141],"derived)":[142],"hierarchical":[143,251],"categorization":[144],"adapt":[149],"notion":[151],"\"shrinkage\"":[153],"-a":[154],"form":[155],"smoothing":[157],"been":[160],"used":[161],"successfully":[162],"classification-to":[165],"construction":[169],"task.":[170],"A":[171],"thorough":[172],"evaluation":[173],"315":[175],"real":[176],"web":[177],"as":[179,181,257],"well":[180],"TREC":[183,225],"data":[184,226],"suggests":[185],"shrinkage-based":[188,237],"substantially":[192],"more":[193],"complete":[194],"than":[195],"\"unshrunk\"":[197],"counterparts.":[198],"We":[199],"also":[200,246],"describe":[201],"how":[202],"modify":[204],"existing":[205],"adaptively":[210],"decide":[211],"-at":[212],"run-time-whether":[213],"apply":[215],"shrinkage":[216],"query.":[219],"Our":[220],"experiments,":[221],"rely":[223],"sets,":[227],"queries,":[228],"associated":[231],"\"relevance":[232],"judgments,\"":[233],"show":[234],"our":[236],"approach":[238],"significantly":[239],"improves":[240],"state-of-the-art":[241],"algorithms,":[244],"outperforms":[247],"recently":[249],"proposed":[250],"strategy":[252],"exploits":[254],"classification":[256],"well.":[258]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}