{"id":"https://openalex.org/W2144687917","doi":"https://doi.org/10.1145/2063576.2063628","title":"Factorization-based lossless compression of inverted indices","display_name":"Factorization-based lossless compression of inverted indices","publication_year":2011,"publication_date":"2011-10-24","ids":{"openalex":"https://openalex.org/W2144687917","doi":"https://doi.org/10.1145/2063576.2063628","mag":"2144687917"},"language":"en","primary_location":{"id":"doi:10.1145/2063576.2063628","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063628","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/A5047755628","display_name":"George Beskales","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":"George Beskales","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073768909","display_name":"Marcus Fontoura","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marcus Fontoura","raw_affiliation_strings":["Google Inc., Mountain View, CA, USA","Google Inc., Mountain View, CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086993894","display_name":"Maxim Gurevich","orcid":"https://orcid.org/0000-0003-4693-0556"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maxim Gurevich","raw_affiliation_strings":["Yahoo! Labs, Santa Clara, CA, USA","Yahoo! Labs., Santa Clara, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Labs., Santa Clara, CA, USA#TAB#","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070795618","display_name":"Sergei Vassilvitskii","orcid":"https://orcid.org/0000-0003-0235-1624"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergei Vassilvitskii","raw_affiliation_strings":["Yahoo! Labs, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, New York, NY, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037908462","display_name":"Vanja Josifovski","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vanja Josifovski","raw_affiliation_strings":["Yahoo! Labs, Santa Clara, CA, USA","Yahoo! Labs., Santa Clara, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Labs., Santa Clara, CA, USA#TAB#","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9363,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76090921,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"327","last_page":"332"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9994999766349792,"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":0.9994999766349792,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9994000196456909,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9958000183105469,"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/inverted-index","display_name":"Inverted index","score":0.8082345724105835},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.7756446003913879},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6162917017936707},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6083316206932068},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.531633734703064},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5196838974952698},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.49956750869750977},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4903581142425537},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.4786754250526428},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.44925978779792786},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.44168925285339355},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41387248039245605},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.3854770064353943},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.23818209767341614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20706939697265625}],"concepts":[{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.8082345724105835},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.7756446003913879},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6162917017936707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6083316206932068},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.531633734703064},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5196838974952698},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.49956750869750977},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4903581142425537},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.4786754250526428},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.44925978779792786},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.44168925285339355},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41387248039245605},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3854770064353943},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.23818209767341614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20706939697265625},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2063576.2063628","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063628","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1532325895","https://openalex.org/W1562327279","https://openalex.org/W1576347883","https://openalex.org/W1880262756","https://openalex.org/W1967838552","https://openalex.org/W1982858363","https://openalex.org/W2006997130","https://openalex.org/W2012961725","https://openalex.org/W2025690557","https://openalex.org/W2032866865","https://openalex.org/W2036216970","https://openalex.org/W2038807029","https://openalex.org/W2080090262","https://openalex.org/W2116148865","https://openalex.org/W2118718620","https://openalex.org/W2135029798","https://openalex.org/W2135290016","https://openalex.org/W2138662031","https://openalex.org/W2144544802","https://openalex.org/W2144687917","https://openalex.org/W2147152072","https://openalex.org/W2148694408","https://openalex.org/W2152437528","https://openalex.org/W2153622543","https://openalex.org/W2154610494","https://openalex.org/W2155981690","https://openalex.org/W2571268788","https://openalex.org/W2666600683","https://openalex.org/W2950549866","https://openalex.org/W3143596294","https://openalex.org/W4205680171","https://openalex.org/W4213009331","https://openalex.org/W4292023222","https://openalex.org/W4320800818","https://openalex.org/W6680012447"],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2778153218","https://openalex.org/W1531601525","https://openalex.org/W2898722594","https://openalex.org/W2113856999","https://openalex.org/W4391266752","https://openalex.org/W133838137","https://openalex.org/W2756819747"],"abstract_inverted_index":{"Many":[0],"large-scale":[1],"Web":[2],"applications":[3],"that":[4,94],"require":[5],"ranked":[6],"top-k":[7],"retrieval":[8],"are":[9],"implemented":[10],"using":[11],"inverted":[12,15,42,75],"indices.":[13,43],"An":[14],"index":[16],"represents":[17],"a":[18,49,53,72,83,88,105,141],"sparse":[19],"term-document":[20,29,68],"matrix,":[21,69],"where":[22],"non-zero":[23,64],"elements":[24,65],"indicate":[25],"the":[26,61,67,79,96,121,126],"strength":[27],"of":[28,41,63,81,116,123,152],"associations.":[30],"In":[31],"this":[32],"work,":[33],"we":[34,139],"present":[35],"an":[36,100,110],"approach":[37,45,118],"for":[38,108,143],"lossless":[39],"compression":[40,154],"Our":[44],"maps":[46],"terms":[47,124],"in":[48,57,66,71,125],"document":[50],"corpus":[51],"to":[52,59],"new":[54,84],"term":[55,85],"space":[56,86],"order":[58],"reduce":[60],"number":[62,122],"resulting":[70],"more":[73],"compact":[74],"index.":[76],"We":[77,103],"formulate":[78],"problem":[80],"selecting":[82],"as":[87],"matrix":[89],"factorization":[90],"problem,":[91],"and":[92],"prove":[93],"finding":[95,109],"optimal":[97],"solution":[98],"is":[99,119],"NP-hard":[101],"problem.":[102],"develop":[104,140],"greedy":[106],"algorithm":[107],"approximate":[111],"solution.":[112],"A":[113],"side":[114],"effect":[115],"our":[117,153],"increasing":[120],"index,":[127],"which":[128],"may":[129],"negatively":[130],"affect":[131],"query":[132,145],"evaluation":[133,146],"performance.":[134],"To":[135],"eliminate":[136],"such":[137],"effect,":[138],"methodology":[142],"modifying":[144],"algorithms":[147],"by":[148],"exploiting":[149],"specific":[150],"properties":[151],"approach.":[155]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}