{"id":"https://openalex.org/W2147671191","doi":"https://doi.org/10.1145/1148170.1148233","title":"Hybrid index maintenance for growing text collections","display_name":"Hybrid index maintenance for growing text collections","publication_year":2006,"publication_date":"2006-08-06","ids":{"openalex":"https://openalex.org/W2147671191","doi":"https://doi.org/10.1145/1148170.1148233","mag":"2147671191"},"language":"en","primary_location":{"id":"doi:10.1145/1148170.1148233","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148233","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 annual international ACM SIGIR conference on Research and development in information retrieval","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/A5033673650","display_name":"Stefan B\u00fcttcher","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Stefan B\u00fcttcher","raw_affiliation_strings":["University of Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037737168","display_name":"Charles L. A. Clarke","orcid":"https://orcid.org/0000-0001-8178-9194"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Charles L. A. Clarke","raw_affiliation_strings":["University of Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073426637","display_name":"Brad Lushman","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Brad Lushman","raw_affiliation_strings":["University of Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033673650"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":8.8389,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.97659292,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"356","last_page":"363"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"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/T11106","display_name":"Data Management and Algorithms","score":0.9984999895095825,"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":0.9983000159263611,"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/search-engine-indexing","display_name":"Search engine indexing","score":0.8240451216697693},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8091671466827393},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.72892165184021},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.6613607406616211},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.4957343339920044},{"id":"https://openalex.org/keywords/auxiliary-memory","display_name":"Auxiliary memory","score":0.44887402653694153},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4470222592353821},{"id":"https://openalex.org/keywords/zipfs-law","display_name":"Zipf's law","score":0.44561341404914856},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4304739534854889},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14113613963127136},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10972049832344055},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0931018590927124}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8240451216697693},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8091671466827393},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.72892165184021},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.6613607406616211},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.4957343339920044},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.44887402653694153},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4470222592353821},{"id":"https://openalex.org/C125932096","wikidata":"https://www.wikidata.org/wiki/Q205472","display_name":"Zipf's law","level":2,"score":0.44561341404914856},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4304739534854889},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14113613963127136},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10972049832344055},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0931018590927124},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1148170.1148233","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148233","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 annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.61.9983","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.61.9983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://stefan.buettcher.org/papers/buettcher_2006_hybrid_index_maintenance_2.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.46000000834465027,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1570431431","https://openalex.org/W1596958800","https://openalex.org/W1986447815","https://openalex.org/W1993666611","https://openalex.org/W1997139601","https://openalex.org/W2016576449","https://openalex.org/W2038807029","https://openalex.org/W2049342105","https://openalex.org/W2079656678","https://openalex.org/W2082272976","https://openalex.org/W2121854496","https://openalex.org/W2122416857","https://openalex.org/W2124575832","https://openalex.org/W2140795521","https://openalex.org/W2142009257","https://openalex.org/W2163652601","https://openalex.org/W2963445511","https://openalex.org/W6635719136"],"related_works":["https://openalex.org/W3123832408","https://openalex.org/W2137719806","https://openalex.org/W2744330362","https://openalex.org/W2096748633","https://openalex.org/W2963431268","https://openalex.org/W3131094596","https://openalex.org/W2146223937","https://openalex.org/W2063584014","https://openalex.org/W1568990036","https://openalex.org/W2024886718"],"abstract_inverted_index":{"We":[0,123],"present":[1,125],"a":[2,57,126,133],"new":[3,23,42,93],"family":[4],"of":[5,73,82,91,105,113,140,155,163],"hybrid":[6,30,84,147],"index":[7,15,31,98],"maintenance":[8,32,99,148],"strategies":[9,24],"to":[10,103,117],"be":[11],"used":[12],"in":[13,33,152],"on-line":[14],"construction":[16],"for":[17,29],"monotonically":[18],"growing":[19],"text":[20,35,157],"collections.":[21],"These":[22],"improve":[25],"upon":[26],"recent":[27],"results":[28],"dynamic":[34],"retrieval":[36],"systems.":[37],"Like":[38],"previous":[39,83],"techniques,":[40],"our":[41],"method":[43],"distinguishes":[44],"between":[45],"short":[46,52],"and":[47,65,86],"long":[48,60,74],"posting":[49,75],"lists:":[50],"While":[51],"lists":[53,61,76],"are":[54,62,66,77],"maintained":[55],"using":[56],"merge":[58],"strategy,":[59],"kept":[63],"separate":[64],"updated":[67],"in-place.":[68],"This":[69],"way,":[70],"costly":[71],"relocations":[72],"avoided.We":[78],"discuss":[79],"the":[80,92,106,111,118,137,145,153,156,160,164],"shortcomings":[81],"methods":[85],"give":[87],"an":[88],"experimental":[89],"evaluation":[90],"technique,":[94],"showing":[95],"that":[96,104],"its":[97],"performance":[100],"is":[101,121,150],"superior":[102],"earlier":[107],"methods,":[108],"especially":[109],"when":[110],"amount":[112],"main":[114],"memory":[115],"available":[116],"indexing":[119],"system":[120],"small.":[122],"also":[124],"complexity":[127],"analysis":[128],"which":[129],"proves":[130],"that,":[131],"under":[132],"Zipfian":[134],"term":[135],"distribution,":[136],"asymptotical":[138,161],"number":[139],"disk":[141],"accesses":[142],"performed":[143],"by":[144],"best":[146],"strategy":[149],"linear":[151],"size":[154],"collection,":[158],"implying":[159],"optimality":[162],"proposed":[165],"strategy.":[166]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}