{"id":"https://openalex.org/W2591309672","doi":"https://doi.org/10.3390/a10010030","title":"Towards Efficient Positional Inverted Index \u2020","display_name":"Towards Efficient Positional Inverted Index \u2020","publication_year":2017,"publication_date":"2017-02-22","ids":{"openalex":"https://openalex.org/W2591309672","doi":"https://doi.org/10.3390/a10010030","mag":"2591309672"},"language":"en","primary_location":{"id":"doi:10.3390/a10010030","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a10010030","pdf_url":"https://www.mdpi.com/1999-4893/10/1/30/pdf","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/10/1/30/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101417106","display_name":"P. Proch\u00e1zka","orcid":"https://orcid.org/0000-0001-5604-0501"},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Petr Proch\u00e1zka","raw_affiliation_strings":["Current address: Th\u00e1kurova 2700/9, 16000 Praha 6, Czech Republic","Department of Theoretical Computer Science, Faculty of Information Technology, Czech Technical University in Prague, Prague 16000, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Current address: Th\u00e1kurova 2700/9, 16000 Praha 6, Czech Republic","institution_ids":[]},{"raw_affiliation_string":"Department of Theoretical Computer Science, Faculty of Information Technology, Czech Technical University in Prague, Prague 16000, Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030676152","display_name":"Jan Holub","orcid":"https://orcid.org/0000-0003-3022-2694"},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Holub","raw_affiliation_strings":["Current address: Th\u00e1kurova 2700/9, 16000 Praha 6, Czech Republic","Department of Theoretical Computer Science, Faculty of Information Technology, Czech Technical University in Prague, Prague 16000, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Current address: Th\u00e1kurova 2700/9, 16000 Praha 6, Czech Republic","institution_ids":[]},{"raw_affiliation_string":"Department of Theoretical Computer Science, Faculty of Information Technology, Czech Technical University in Prague, Prague 16000, Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101417106"],"corresponding_institution_ids":["https://openalex.org/I44504214"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.2064,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59343379,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"10","issue":"1","first_page":"30","last_page":"30"},"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9944999814033508,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.8267598748207092},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5559697151184082},{"id":"https://openalex.org/keywords/huffman-coding","display_name":"Huffman coding","score":0.5456405878067017},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.537788450717926},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.4864668548107147},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.4419366717338562},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4170008897781372},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32555341720581055},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23409804701805115},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.19989868998527527},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.17035844922065735},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.14692279696464539}],"concepts":[{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.8267598748207092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5559697151184082},{"id":"https://openalex.org/C46900642","wikidata":"https://www.wikidata.org/wiki/Q2647","display_name":"Huffman coding","level":3,"score":0.5456405878067017},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.537788450717926},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.4864668548107147},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4419366717338562},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4170008897781372},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32555341720581055},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23409804701805115},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.19989868998527527},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17035844922065735},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.14692279696464539},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/a10010030","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a10010030","pdf_url":"https://www.mdpi.com/1999-4893/10/1/30/pdf","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ad68ea04c5f046949200a0b1c5728bad","is_oa":true,"landing_page_url":"https://doaj.org/article/ad68ea04c5f046949200a0b1c5728bad","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms, Vol 10, Iss 1, p 30 (2017)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1999-4893/10/1/30/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/a10010030","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms; Volume 10; Issue 1; Pages: 30","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/a10010030","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a10010030","pdf_url":"https://www.mdpi.com/1999-4893/10/1/30/pdf","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2591309672.pdf","grobid_xml":"https://content.openalex.org/works/W2591309672.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1494592156","https://openalex.org/W1970765735","https://openalex.org/W1971520389","https://openalex.org/W1976656104","https://openalex.org/W1989227656","https://openalex.org/W2028009320","https://openalex.org/W2038807029","https://openalex.org/W2055663575","https://openalex.org/W2087361130","https://openalex.org/W2088386938","https://openalex.org/W2115613939","https://openalex.org/W2128777897","https://openalex.org/W2138662031","https://openalex.org/W2142905080","https://openalex.org/W4255256386","https://openalex.org/W6674809819"],"related_works":["https://openalex.org/W3209232512","https://openalex.org/W2058987221","https://openalex.org/W2145657320","https://openalex.org/W2102493899","https://openalex.org/W2388346754","https://openalex.org/W2082146874","https://openalex.org/W4282568653","https://openalex.org/W2187610212","https://openalex.org/W2123678380","https://openalex.org/W180545237"],"abstract_inverted_index":{"We":[0],"address":[1],"the":[2,8,17,20,29,42,51,73,76,82,85,89,111,121,128,188,192,198,201,213,275,289],"problem":[3],"of":[4,19,62,75,84,88,110,127,174,180,187,200,203,212,264,277,291],"positional":[5,13],"indexing":[6],"in":[7,191,207],"natural":[9],"language":[10],"domain.":[11],"The":[12,92,114,124,209],"inverted":[14,69,93,130,193],"index":[15],"contains":[16],"information":[18],"word":[21,52,202,281],"positions.":[22],"Thus,":[23],"it":[24,36,80],"is":[25,37,95,117,132,171,177,184,197,216],"able":[26],"to":[27,40,119,254],"recover":[28],"original":[30,43,90],"text":[31,77],"file,":[32],"which":[33],"implies":[34],"that":[35,71,101],"not":[38],"necessary":[39],"store":[41],"file.":[44,91],"Our":[45],"Positional":[46],"Inverted":[47,60],"Self-Index":[48],"(PISI)":[49],"stores":[50,81,102],"position":[53,269,283],"gaps":[54],"encoded":[55],"by":[56],"variable":[57],"byte":[58],"code.":[59],"lists":[61],"single":[63],"terms":[64],"are":[65],"combined":[66],"into":[67],"one":[68],"list":[70,94,131,194],"represents":[72],"backbone":[74],"file":[78],"since":[79],"sequence":[83],"indexed":[86,112],"words":[87],"synchronized":[96],"with":[97,252],"a":[98,172,178,185,262,265],"presentation":[99,122,214],"layer":[100,215],"separators,":[103],"stop":[104,280,294],"words,":[105],"as":[106,108,261,274,288],"well":[107],"variants":[109],"words.":[113,295],"Huffman":[115],"coding":[116],"used":[118],"encode":[120],"layer.":[123],"space":[125,210],"complexity":[126,211],"PISI":[129],"O":[133,217],"(":[134,135,147,158,218,231,258],"N":[136,144,149,170,224,240,250,286],"\u2212":[137,150,219,235],"n":[138,151,155,163,176,230,257],")":[139,156,167,168,233,251,260],"\u2308":[140,159,225,242],"log":[141,160,226,243],"2":[142,161,227,244],"b":[143,162,196],"\u2309":[145,164,234,248],"+":[146,154,165,249],"\u230a":[148],"\u03b1":[152,183],"\u230b":[153],"\u00d7":[157],"1":[166,223,239],"where":[169],"number":[173,179,290],"stems,":[175,182],"unique":[181],"step/period":[186],"back":[189],"pointers":[190],"and":[195,285,293],"size":[199],"computer":[204],"memory":[205],"given":[206],"bits.":[208],"\u2211":[220,236],"i":[221,229,232,256,259],"=":[222,238],"p":[228,245,255,271],"j":[237,246,272,284],"\u2032":[241,247,273,287],"respect":[253],"probability":[263,276],"stem":[266],"variant":[267],"at":[268,282],"i,":[270],"separator":[278],"or":[279],"separators":[292]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
