{"id":"https://openalex.org/W2042130547","doi":"https://doi.org/10.1145/1008992.1009046","title":"Assigning identifiers to documents to enhance the clustering property of fulltext indexes","display_name":"Assigning identifiers to documents to enhance the clustering property of fulltext indexes","publication_year":2004,"publication_date":"2004-07-25","ids":{"openalex":"https://openalex.org/W2042130547","doi":"https://doi.org/10.1145/1008992.1009046","mag":"2042130547"},"language":"en","primary_location":{"id":"doi:10.1145/1008992.1009046","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th 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/A5044165871","display_name":"Fabrizio Silvestri","orcid":"https://orcid.org/0000-0001-7669-9055"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Fabrizio Silvestri","raw_affiliation_strings":["Universit\u00e0 di Pisa, Italy","Universita di Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]},{"raw_affiliation_string":"Universita di Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066317336","display_name":"Salvatore Orlando","orcid":"https://orcid.org/0000-0002-4155-9797"},"institutions":[{"id":"https://openalex.org/I11986463","display_name":"Universit\u00e0 Iuav di Venezia","ror":"https://ror.org/01e6ksd91","country_code":"IT","type":"education","lineage":["https://openalex.org/I11986463"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Salvatore Orlando","raw_affiliation_strings":["Universit\u00e0 di Venezia, Mestre, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Venezia, Mestre, Italy","institution_ids":["https://openalex.org/I11986463"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035605298","display_name":"Raffaele Perego","orcid":"https://orcid.org/0000-0001-7189-4724"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Raffaele Perego","raw_affiliation_strings":["ISTI - CNR, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"ISTI - CNR, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5044165871"],"corresponding_institution_ids":["https://openalex.org/I108290504"],"apc_list":null,"apc_paid":null,"fwci":4.6948,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.94685554,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"305","last_page":"312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9972000122070312,"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/T10742","display_name":"Peer-to-Peer Network Technologies","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":0.8518029451370239},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.7206335067749023},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6886811256408691},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.631658673286438},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6185916662216187},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5792230367660522},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5662164688110352},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5449565052986145},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.36786797642707825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2470291554927826},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.13187462091445923},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10039576888084412}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8518029451370239},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.7206335067749023},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6886811256408691},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.631658673286438},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6185916662216187},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5792230367660522},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5662164688110352},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5449565052986145},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.36786797642707825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2470291554927826},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.13187462091445923},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10039576888084412}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1008992.1009046","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:dnet:people______::df5ed953c3fb2e4d22723fd215b3c12c","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331528","display_name":"Ministero dell'Universit\u00e0 e della Ricerca","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W191231183","https://openalex.org/W1506845741","https://openalex.org/W1559631118","https://openalex.org/W1575155361","https://openalex.org/W1669813703","https://openalex.org/W1759973002","https://openalex.org/W1996764654","https://openalex.org/W1997841190","https://openalex.org/W2005677600","https://openalex.org/W2015662797","https://openalex.org/W2022292926","https://openalex.org/W2038807029","https://openalex.org/W2052867877","https://openalex.org/W2160484851","https://openalex.org/W2621280964","https://openalex.org/W4241122026","https://openalex.org/W6634503373"],"related_works":["https://openalex.org/W4378651134","https://openalex.org/W2124379162","https://openalex.org/W4252684102","https://openalex.org/W2352307597","https://openalex.org/W1979633005","https://openalex.org/W2163724607","https://openalex.org/W3135403405","https://openalex.org/W2608983118","https://openalex.org/W1980092392","https://openalex.org/W2015662797"],"abstract_inverted_index":{"Web":[0],"Search":[1],"Engines":[2],"provide":[3],"a":[4],"large-scale":[5],"text":[6],"document":[7,57],"retrieval":[8],"service":[9],"by":[10,37],"processing":[11],"huge":[12],"Inverted":[13,16],"File":[14,17],"indexes.":[15],"indexes":[18],"allow":[19],"fast":[20],"query":[21],"resolution":[22],"and":[23,34,46,95],"good":[24],"memory":[25],"utilization":[26],"since":[27],"their":[28],"d-gaps":[29],"representation":[30],"can":[31],"be":[32],"effectively":[33],"efficiently":[35],"compressed":[36],"using":[38],"variable":[39],"length":[40],"encoding":[41,118],"methods.":[42,73],"This":[43],"paper":[44],"proposes":[45],"evaluates":[47],"some":[48],"algorithms":[49],"aimed":[50],"to":[51,85,107,111],"find":[52],"an":[53],"assignment":[54],"of":[55,64,70,97,116],"the":[56,61,68,79,87,93,101,113],"identifiers":[58],"which":[59],"minimizes":[60],"average":[62],"values":[63],"d-gaps,":[65],"thus":[66],"enhancing":[67],"effectiveness":[69,96],"traditional":[71],"compression":[72,114],"We":[74],"ran":[75],"several":[76,117],"tests":[77],"over":[78],"Google":[80],"contest":[81],"collection":[82],"in":[83],"order":[84],"validate":[86],"techniques":[88],"proposed.":[89],"The":[90],"experiments":[91],"demonstrated":[92],"scalability":[94],"our":[98],"algorithms.":[99],"Using":[100],"proposed":[102],"algorithms,":[103],"we":[104],"were":[105],"able":[106],"sensibly":[108],"improve":[109],"(up":[110],"20.81%)":[112],"ratios":[115],"schemes.":[119]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"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"}