{"id":"https://openalex.org/W2026355363","doi":"https://doi.org/10.1145/1871437.1871527","title":"Index structures for efficiently searching natural language text","display_name":"Index structures for efficiently searching natural language text","publication_year":2010,"publication_date":"2010-10-26","ids":{"openalex":"https://openalex.org/W2026355363","doi":"https://doi.org/10.1145/1871437.1871527","mag":"2026355363"},"language":"en","primary_location":{"id":"doi:10.1145/1871437.1871527","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th 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/A5029609490","display_name":"Pirooz Chubak","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Pirooz Chubak","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071837282","display_name":"Davood Rafiei","orcid":"https://orcid.org/0000-0003-2403-0266"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Davood Rafiei","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029609490"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":1.3965,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84598985,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"689","last_page":"698"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9937000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8740068078041077},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7398921847343445},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.6680682301521301},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5993252992630005},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.558815598487854},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5393772721290588},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5299606919288635},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5196134448051453},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.516630232334137},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5001111030578613},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4892897307872772},{"id":"https://openalex.org/keywords/parse-tree","display_name":"Parse tree","score":0.48629316687583923},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4541867971420288},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4439041018486023},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42192861437797546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39391517639160156},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3283580243587494},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1929064393043518},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13981735706329346},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10188853740692139}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8740068078041077},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7398921847343445},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.6680682301521301},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5993252992630005},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.558815598487854},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5393772721290588},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5299606919288635},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5196134448051453},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.516630232334137},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5001111030578613},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4892897307872772},{"id":"https://openalex.org/C2781466058","wikidata":"https://www.wikidata.org/wiki/Q627921","display_name":"Parse tree","level":3,"score":0.48629316687583923},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4541867971420288},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4439041018486023},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42192861437797546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39391517639160156},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3283580243587494},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1929064393043518},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13981735706329346},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10188853740692139},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1871437.1871527","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.353.5895","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.353.5895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://webdocs.cs.ualberta.ca/~drafiei/papers/cikm10-chubak.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W122707235","https://openalex.org/W142212369","https://openalex.org/W1532325895","https://openalex.org/W1554611468","https://openalex.org/W1981732427","https://openalex.org/W1982858363","https://openalex.org/W1985174631","https://openalex.org/W2006608770","https://openalex.org/W2049652268","https://openalex.org/W2069906566","https://openalex.org/W2088386938","https://openalex.org/W2115461474","https://openalex.org/W2116066543","https://openalex.org/W2133137130","https://openalex.org/W2133953554","https://openalex.org/W2134696992","https://openalex.org/W2137286708","https://openalex.org/W2154148563","https://openalex.org/W2159647614","https://openalex.org/W2161488606","https://openalex.org/W2162076845","https://openalex.org/W6679642144"],"related_works":["https://openalex.org/W3157284875","https://openalex.org/W2259406085","https://openalex.org/W2099715052","https://openalex.org/W2147241511","https://openalex.org/W4226247999","https://openalex.org/W4213176082","https://openalex.org/W2187398150","https://openalex.org/W3209772662","https://openalex.org/W4200629926","https://openalex.org/W4220955952"],"abstract_inverted_index":{"Many":[0],"existing":[1],"indexes":[2],"on":[3,67,144],"text":[4,113],"work":[5],"at":[6],"the":[7,16,21,38,46,89,107,163,168],"document":[8],"granularity":[9],"and":[10,57,79,82,115,132],"are":[11,42],"not":[12],"effective":[13],"in":[14],"answering":[15,45],"class":[17,47,70],"of":[18,37,44,48,61,71,88,92,106,124,156],"queries":[19,49,56,72,151],"where":[20],"desired":[22],"answer":[23],"is":[24,103,128,133,166],"only":[25],"a":[26,29,68,121,145,153],"term":[27],"or":[28],"phrase.":[30],"In":[31],"this":[32,118],"paper,":[33],"we":[34],"study":[35],"some":[36,87],"index":[39,109,119],"structures":[40],"that":[41,117],"capable":[43],"referred":[50],"to":[51,130,141],"here":[52],"as":[53],"wild":[54,125,149],"card":[55,126,150],"perform":[58],"an":[59,104],"analysis":[60],"their":[62],"performance.":[63],"Our":[64,136],"experimental":[65,137],"results":[66],"large":[69],"from":[73],"different":[74],"sources":[75],"(including":[76],"query":[77],"logs":[78],"parse":[80],"trees)":[81],"with":[83],"various":[84],"datasets":[85],"reveal":[86],"performance":[90],"barriers":[91],"these":[93],"indexes.":[94],"We":[95],"then":[96],"present":[97],"Word":[98],"Permuterm":[99],"Index":[100],"(WPI)":[101],"which":[102],"adaptation":[105],"permuterm":[108],"for":[110,160,170],"natural":[111],"language":[112],"applications":[114],"show":[116,152],"supports":[120],"wide":[122,146],"range":[123,147],"queries,":[127],"quick":[129],"construct":[131],"highly":[134],"scalable.":[135],"resultS":[138],"comparing":[139],"WPI":[140,161],"alternative":[142],"methods":[143],"oF":[148],"few":[154],"orders":[155],"magnitude":[157],"performancE":[158],"improvements":[159],"while":[162],"memory":[164],"usage":[165],"kept":[167],"same":[169],"all":[171],"compared":[172],"systems.":[173]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}