{"id":"https://openalex.org/W2771857218","doi":"https://doi.org/10.1145/3166072.3166080","title":"Efficient In-Memory, List-Based Text Inversion","display_name":"Efficient In-Memory, List-Based Text Inversion","publication_year":2017,"publication_date":"2017-12-07","ids":{"openalex":"https://openalex.org/W2771857218","doi":"https://doi.org/10.1145/3166072.3166080","mag":"2771857218"},"language":"en","primary_location":{"id":"doi:10.1145/3166072.3166080","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3166072.3166080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd Australasian Document Computing Symposium","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/A5032211209","display_name":"David Hawking","orcid":"https://orcid.org/0000-0002-3704-5398"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"David Hawking","raw_affiliation_strings":["Microsoft, Canberra, ACT, Australia"],"affiliations":[{"raw_affiliation_string":"Microsoft, Canberra, ACT, Australia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090703924","display_name":"Bodo Billerbeck","orcid":"https://orcid.org/0000-0002-9311-8504"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bodo Billerbeck","raw_affiliation_strings":["Microsoft, Melbourne, Victoria, Australia"],"affiliations":[{"raw_affiliation_string":"Microsoft, Melbourne, Victoria, Australia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5032211209"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6216,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7354466,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994999766349792,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"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/T11478","display_name":"Caching and Content Delivery","score":0.9972000122070312,"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":0.8710346221923828},{"id":"https://openalex.org/keywords/chunking","display_name":"Chunking (psychology)","score":0.7562326192855835},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.5666619539260864},{"id":"https://openalex.org/keywords/traverse","display_name":"Traverse","score":0.5066031217575073},{"id":"https://openalex.org/keywords/demand-paging","display_name":"Demand paging","score":0.4967997372150421},{"id":"https://openalex.org/keywords/virtual-memory","display_name":"Virtual memory","score":0.48673179745674133},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4850468039512634},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.4761604964733124},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4674326777458191},{"id":"https://openalex.org/keywords/flat-memory-model","display_name":"Flat memory model","score":0.43564897775650024},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.31337812542915344},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.22983774542808533},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20889684557914734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1727617383003235},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.1709173321723938},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.1509031355381012}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8710346221923828},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.7562326192855835},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.5666619539260864},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.5066031217575073},{"id":"https://openalex.org/C188873839","wikidata":"https://www.wikidata.org/wiki/Q5255045","display_name":"Demand paging","level":5,"score":0.4967997372150421},{"id":"https://openalex.org/C76399640","wikidata":"https://www.wikidata.org/wiki/Q189401","display_name":"Virtual memory","level":4,"score":0.48673179745674133},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4850468039512634},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.4761604964733124},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4674326777458191},{"id":"https://openalex.org/C57863822","wikidata":"https://www.wikidata.org/wiki/Q905488","display_name":"Flat memory model","level":4,"score":0.43564897775650024},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.31337812542915344},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.22983774542808533},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20889684557914734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1727617383003235},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.1709173321723938},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.1509031355381012},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3166072.3166080","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3166072.3166080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd Australasian Document Computing Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W185639671","https://openalex.org/W652451802","https://openalex.org/W1493802692","https://openalex.org/W1858013062","https://openalex.org/W1996930216","https://openalex.org/W2038807029","https://openalex.org/W2061231586","https://openalex.org/W2079656678","https://openalex.org/W2123127954","https://openalex.org/W2138662031","https://openalex.org/W2146241244","https://openalex.org/W2263798363","https://openalex.org/W2412976325","https://openalex.org/W2742124187","https://openalex.org/W4240908132","https://openalex.org/W4244061993","https://openalex.org/W6621747756","https://openalex.org/W6670271065","https://openalex.org/W6715587312"],"related_works":["https://openalex.org/W1421493983","https://openalex.org/W2078640694","https://openalex.org/W2016036917","https://openalex.org/W2059368477","https://openalex.org/W71081774","https://openalex.org/W2063839959","https://openalex.org/W4243333834","https://openalex.org/W2993738027","https://openalex.org/W1991450610","https://openalex.org/W1584503625"],"abstract_inverted_index":{"When":[0],"building":[1],"a":[2,8,82],"large":[3],"inverted":[4,49],"file":[5,50],"index":[6,150],"on":[7],"system":[9],"with":[10,85],"effectively":[11],"unlimited":[12],"memory,":[13],"performance":[14,44,66],"may":[15],"be":[16],"constrained":[17],"by":[18],"RAM":[19],"latency.":[20],"To":[21],"optimise":[22],"speed":[23,145],"requires":[24],"an":[25,46],"understanding":[26],"of":[27,33,45,59,67,72,78,111,140,149],"the":[28,43,75,93,100,109,117,123,138],"non-uniform":[29],"memory":[30,61,101,124],"access":[31],"characteristics":[32],"modern":[34],"systems.":[35],"We":[36,64],"address":[37],"three":[38],"main":[39],"techniques":[40,94],"for":[41,103],"improving":[42],"in-memory,":[47],"list-based":[48],"indexer:":[51],"List":[52],"chunking,":[53],"in-chunk":[54],"postings":[55],"compression,":[56],"and":[57,144],"use":[58],"virtual":[60],"\"Large":[62],"Pages\".":[63],"compare":[65],"dynamic":[68],"chunking":[69],"schemes":[70],"capable":[71],"adapting":[73],"to":[74,115,133],"Zipf-like":[76],"distribution":[77],"term":[79],"frequencies.":[80],"Using":[81],"data":[83],"set":[84],"8.5":[86],"billion":[87],"word":[88],"occurrences,":[89],"we":[90],"find":[91],"that":[92],"are":[95],"cumulative.":[96],"Chunking":[97],"almost":[98],"halves":[99,122],"required":[102,114],"linked":[104],"lists,":[105],"while":[106],"dramatically":[107],"reducing":[108],"number":[110],"cache-line":[112],"reads":[113],"traverse":[116],"lists;":[118],"In-chunk":[119],"compression":[120],"further":[121],"footprint,":[125],"though":[126],"it":[127],"does":[128],"not":[129],"make":[130],"much":[131],"difference":[132],"speed;":[134],"Large":[135],"pages":[136],"reduce":[137],"inefficiency":[139],"page":[141],"table":[142],"walks":[143],"up":[146],"both":[147],"phases":[148],"building.":[151]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
