{"id":"https://openalex.org/W2142590039","doi":"https://doi.org/10.1145/2063576.2063646","title":"Indexes for highly repetitive document collections","display_name":"Indexes for highly repetitive document collections","publication_year":2011,"publication_date":"2011-10-24","ids":{"openalex":"https://openalex.org/W2142590039","doi":"https://doi.org/10.1145/2063576.2063646","mag":"2142590039"},"language":"en","primary_location":{"id":"doi:10.1145/2063576.2063646","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and 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/A5091203911","display_name":"Francisco Claude","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":"Francisco Claude","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024008175","display_name":"Antonio Fari\u00f1a","orcid":"https://orcid.org/0000-0001-8263-3298"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Antonio Fari\u00f1a","raw_affiliation_strings":["University of A Coru\u00f1a, A Coru\u00f1a, Spain"],"affiliations":[{"raw_affiliation_string":"University of A Coru\u00f1a, A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065554261","display_name":"Miguel A. Mart\u00ednez\u2010Prieto","orcid":"https://orcid.org/0000-0003-4418-561X"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Miguel A. Mart\u00ednez-Prieto","raw_affiliation_strings":["University of Chile, Santiago, Chile","University of Chile -- Santiago, Chile#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]},{"raw_affiliation_string":"University of Chile -- Santiago, Chile#TAB#","institution_ids":["https://openalex.org/I69737025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080743153","display_name":"Gonzalo Navarro","orcid":"https://orcid.org/0000-0002-2286-741X"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Gonzalo Navarro","raw_affiliation_strings":["University of Chile, Santiago, Chile","University of Chile -- Santiago, Chile#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]},{"raw_affiliation_string":"University of Chile -- Santiago, Chile#TAB#","institution_ids":["https://openalex.org/I69737025"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091203911"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":4.4025,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.94616936,"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":"463","last_page":"468"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"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":1.0,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9966999888420105,"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/T12162","display_name":"Cellular Automata and Applications","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.7400927543640137},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.6878530383110046},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5936325192451477},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5690644383430481},{"id":"https://openalex.org/keywords/software-versioning","display_name":"Software versioning","score":0.4520915448665619},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.4373217225074768},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.4278196692466736},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4268665313720703},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4245392084121704},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37796008586883545},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35941094160079956},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2568874955177307},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14756977558135986},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.10519516468048096},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.07970234751701355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7400927543640137},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.6878530383110046},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5936325192451477},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5690644383430481},{"id":"https://openalex.org/C198140048","wikidata":"https://www.wikidata.org/wiki/Q10859422","display_name":"Software versioning","level":3,"score":0.4520915448665619},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.4373217225074768},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.4278196692466736},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4268665313720703},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4245392084121704},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37796008586883545},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35941094160079956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2568874955177307},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14756977558135986},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.10519516468048096},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.07970234751701355},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2063576.2063646","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.228.4342","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.228.4342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcc.uchile.cl/%7Egnavarro/ps/cikm11.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W77904627","https://openalex.org/W1515851167","https://openalex.org/W1528475610","https://openalex.org/W1529451410","https://openalex.org/W1537796421","https://openalex.org/W1556744446","https://openalex.org/W1561988317","https://openalex.org/W1570532020","https://openalex.org/W1969838114","https://openalex.org/W1971849009","https://openalex.org/W2013849299","https://openalex.org/W2022292926","https://openalex.org/W2022507549","https://openalex.org/W2041824945","https://openalex.org/W2046038806","https://openalex.org/W2061986359","https://openalex.org/W2072021854","https://openalex.org/W2087361130","https://openalex.org/W2088386938","https://openalex.org/W2107745473","https://openalex.org/W2108974085","https://openalex.org/W2136070674","https://openalex.org/W2138662031","https://openalex.org/W2140453381","https://openalex.org/W2602771387"],"related_works":["https://openalex.org/W2124379162","https://openalex.org/W2805651586","https://openalex.org/W1604458106","https://openalex.org/W2970215257","https://openalex.org/W3209232512","https://openalex.org/W1503327463","https://openalex.org/W3112768174","https://openalex.org/W2104956440","https://openalex.org/W2382673214","https://openalex.org/W2110517301"],"abstract_inverted_index":{"We":[0,34],"introduce":[1],"new":[2],"compressed":[3],"inverted":[4,23],"indexes":[5],"for":[6],"highly":[7],"repetitive":[8],"document":[9],"collections.":[10],"They":[11],"are":[12,59],"based":[13],"on":[14],"run-length,":[15],"Lempel-Ziv,":[16],"or":[17],"grammar-based":[18],"compression":[19,38],"of":[20,26,51,56,72],"the":[21,31,42,49,69,73],"differential":[22],"lists,":[24],"instead":[25],"gap-encoding":[27],"them":[28],"as":[29],"is":[30],"usual":[32],"practice.":[33],"show":[35],"that":[36,61],"our":[37,57],"methods":[39,58],"significantly":[40],"reduce":[41],"space":[43],"achieved":[44],"by":[45],"classical":[46],"compression,":[47],"at":[48],"price":[50],"moderate":[52],"slowdowns.":[53],"Moreover,":[54],"many":[55],"universal,":[60],"is,":[62],"they":[63],"do":[64],"not":[65],"need":[66],"to":[67],"know":[68],"versioning":[70],"structure":[71],"collection.":[74]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
