{"id":"https://openalex.org/W2100399044","doi":"https://doi.org/10.1145/2559168","title":"Indexing Word Sequences for Ranked Retrieval","display_name":"Indexing Word Sequences for Ranked Retrieval","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2100399044","doi":"https://doi.org/10.1145/2559168","mag":"2100399044"},"language":"en","primary_location":{"id":"doi:10.1145/2559168","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2559168","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"type":"paratext","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/Indexing_word_sequences_for_ranked_retrieval/27465402","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075934267","display_name":"Samuel Huston","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Huston","raw_affiliation_strings":["University of Massachusetts Amherst","University of Massachusetts: Amherst#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts: Amherst#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070937840","display_name":"J. Shane Culpepper","orcid":"https://orcid.org/0000-0002-1902-9087"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"J. Shane Culpepper","raw_affiliation_strings":["RMIT University","RMIT-University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University","institution_ids":["https://openalex.org/I82951845"]},{"raw_affiliation_string":"RMIT-University","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105659698","display_name":"W. Bruce Croft","orcid":"https://orcid.org/0000-0003-2391-9629"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W. Bruce Croft","raw_affiliation_strings":["University of Massachusetts Amherst","University of Massachusetts: Amherst#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts: Amherst#TAB#","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"1","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":true,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9993000030517578,"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":0.9993000030517578,"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/T11106","display_name":"Data Management and Algorithms","score":0.9990000128746033,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9958000183105469,"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":0.8456374406814575},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7705037593841553},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7470340728759766},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.6668699979782104},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5779325366020203},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.574805498123169},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.5682309865951538},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5630896091461182},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5268046855926514},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5137849450111389},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4426489770412445},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.42015087604522705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33665427565574646},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14507845044136047},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10071301460266113}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8456374406814575},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7705037593841553},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7470340728759766},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.6668699979782104},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5779325366020203},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.574805498123169},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.5682309865951538},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5630896091461182},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5268046855926514},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5137849450111389},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4426489770412445},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.42015087604522705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33665427565574646},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14507845044136047},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10071301460266113},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1145/2559168","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2559168","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.460.4191","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.460.4191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://goanna.cs.rmit.edu.au/~e76763/publications/hcc14-tois.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.651.1098","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.651.1098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://maroo.cs.umass.edu/pub/web/getpdf.php?id=1106","raw_type":"text"},{"id":"pmh:oai:researchbank.rmit.edu.au:rmit:24582","is_oa":false,"landing_page_url":"http://researchbank.rmit.edu.au/view/rmit:24582","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},{"id":"pmh:oai:alma.61RMIT_INST:11246984600001341","is_oa":false,"landing_page_url":"http://doi.org/10.1145/2559168","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:figshare.com:article/27465402","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Indexing_word_sequences_for_ranked_retrieval/27465402","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/27465402","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Indexing_word_sequences_for_ranked_retrieval/27465402","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5231231507","display_name":null,"funder_award_id":"CNS-0934322","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"},{"id":"https://openalex.org/G6004806057","display_name":null,"funder_award_id":"IIS-0844226","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"},{"id":"https://openalex.org/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W27682417","https://openalex.org/W72059462","https://openalex.org/W142567295","https://openalex.org/W151938044","https://openalex.org/W1493892051","https://openalex.org/W1504477191","https://openalex.org/W1564085854","https://openalex.org/W1752316941","https://openalex.org/W1858013062","https://openalex.org/W1917000772","https://openalex.org/W1965972569","https://openalex.org/W1966607771","https://openalex.org/W1976682045","https://openalex.org/W1977141583","https://openalex.org/W1980344365","https://openalex.org/W1981732427","https://openalex.org/W1985471546","https://openalex.org/W1988679864","https://openalex.org/W1995484833","https://openalex.org/W1997214779","https://openalex.org/W1998024002","https://openalex.org/W2000431947","https://openalex.org/W2014318353","https://openalex.org/W2018989507","https://openalex.org/W2025356973","https://openalex.org/W2041666597","https://openalex.org/W2046874737","https://openalex.org/W2048476252","https://openalex.org/W2051158076","https://openalex.org/W2060324268","https://openalex.org/W2065472179","https://openalex.org/W2070507812","https://openalex.org/W2070740689","https://openalex.org/W2076489648","https://openalex.org/W2080234606","https://openalex.org/W2080745194","https://openalex.org/W2085316814","https://openalex.org/W2088386938","https://openalex.org/W2093390569","https://openalex.org/W2096679307","https://openalex.org/W2096961418","https://openalex.org/W2104807347","https://openalex.org/W2108079923","https://openalex.org/W2111046826","https://openalex.org/W2117424365","https://openalex.org/W2119119231","https://openalex.org/W2119455368","https://openalex.org/W2131409447","https://openalex.org/W2133628502","https://openalex.org/W2139433757","https://openalex.org/W2140960149","https://openalex.org/W2141957180","https://openalex.org/W2142905080","https://openalex.org/W2144620640","https://openalex.org/W2148578434","https://openalex.org/W2149530645","https://openalex.org/W2154610494","https://openalex.org/W2160484851","https://openalex.org/W2165718308","https://openalex.org/W2263798363","https://openalex.org/W2295820528","https://openalex.org/W2466240490","https://openalex.org/W2550271127","https://openalex.org/W2580302247","https://openalex.org/W2618735189","https://openalex.org/W2621280964","https://openalex.org/W3215633023","https://openalex.org/W4206765718","https://openalex.org/W4230402390","https://openalex.org/W4248708867","https://openalex.org/W4389615622"],"related_works":["https://openalex.org/W2058987221","https://openalex.org/W2145657320","https://openalex.org/W2102493899","https://openalex.org/W2388346754","https://openalex.org/W4282568653","https://openalex.org/W2187610212","https://openalex.org/W2399928914","https://openalex.org/W2123678380","https://openalex.org/W180545237","https://openalex.org/W1837234277"],"abstract_inverted_index":{"Formulating":[0],"and":[1,4,41,54,149,193],"processing":[2,28],"phrases":[3],"other":[5],"term":[6],"dependencies":[7],"to":[8,61,90,117,157],"improve":[9,46,62],"query":[10,63],"effectiveness":[11],"is":[12,113],"an":[13,140],"important":[14,94],"problem":[15],"in":[16,65,84,95,187],"information":[17],"retrieval.":[18],"However,":[19],"accessing":[20],"word-sequence":[21],"statistics":[22,93],"using":[23],"inverted":[24],"indexes":[25],"requires":[26],"unreasonable":[27],"time":[29,42],"or":[30],"substantial":[31],"space":[32,40,105,133,163],"overhead.":[33],"Establishing":[34],"a":[35,56,71,169],"balance":[36],"between":[37,147],"these":[38],"competing":[39],"trade-offs":[43],"can":[44,130,180],"dramatically":[45],"system":[47],"performance.":[48],"In":[49],"this":[50],"article,":[51],"we":[52,87,124],"present":[53],"analyze":[55],"new":[57],"index":[58,112,129,141],"structure":[59],"designed":[60],"efficiency":[64],"dependency":[66],"retrieval":[67],"models.":[68],"By":[69],"adapting":[70],"class":[72],"of":[73,110,120,135,139,142,146,161,165,168],"(":[74],"\u03b5,":[75],"\u03b4":[76],")-approximation":[77],"algorithms":[78],"originally":[79],"proposed":[80],"for":[81,107],"sketch":[82,128],"summarization":[83],"networking":[85],"applications,":[86],"show":[88,125,174],"how":[89],"accurately":[91],"estimate":[92],"term-dependency":[96],"models":[97],"with":[98],"low,":[99],"probabilistically":[100],"bounded":[101],"error":[102],"rates.":[103],"The":[104],"requirements":[106,134,164],"the":[108,111,118,121,127,132,136,154,162,166],"vocabulary":[109,137,167],"only":[114],"logarithmically":[115],"linked":[116],"size":[119],"vocabulary.":[122],"Empirically,":[123],"that":[126,175],"reduce":[131],"component":[138],"n":[143,177],"-grams":[144],"consisting":[145],"1":[148],"4":[150],"words":[151],"extracted":[152],"from":[153],"GOV2":[155],"collection":[156],"less":[158],"than":[159,186],"0.01%":[160],"full":[170],"index.":[171],"We":[172],"also":[173],"larger":[176],"-gram":[178],"queries":[179],"be":[181],"processed":[182],"considerably":[183],"more":[184],"efficiently":[185],"current":[188],"alternatives,":[189],"such":[190],"as":[191],"positional":[192],"next-word":[194],"indexes.":[195]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}
