{"id":"https://openalex.org/W2048102545","doi":"https://doi.org/10.1145/2806416.2806467","title":"On the Cost of Extracting Proximity Features for Term-Dependency Models","display_name":"On the Cost of Extracting Proximity Features for Term-Dependency Models","publication_year":2015,"publication_date":"2015-10-17","ids":{"openalex":"https://openalex.org/W2048102545","doi":"https://doi.org/10.1145/2806416.2806467","mag":"2048102545"},"language":"en","primary_location":{"id":"doi:10.1145/2806416.2806467","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2806416.2806467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/11343/58271","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103166668","display_name":"Xiaolu Lu","orcid":"https://orcid.org/0000-0002-2092-5460"},"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":true,"raw_author_name":"Xiaolu Lu","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081861848","display_name":"Alistair Moffat","orcid":"https://orcid.org/0000-0002-6638-0232"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Alistair Moffat","raw_affiliation_strings":["The University of Melbourne, Melbourne, Australia","The University of Melbourne, Melbourne, Australia;"],"affiliations":[{"raw_affiliation_string":"The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"The University of Melbourne, Melbourne, Australia;","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","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, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103166668"],"corresponding_institution_ids":["https://openalex.org/I82951845"],"apc_list":null,"apc_paid":null,"fwci":4.9322,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.95172414,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"293","last_page":"302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9983999729156494,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.7771987915039062},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6253748536109924},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.6195798516273499},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5786734819412231},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.558508038520813},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5562164187431335},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5120623707771301},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4671119451522827},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.4577741324901581},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4547429084777832},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.41071611642837524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3013785183429718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7771987915039062},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6253748536109924},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.6195798516273499},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5786734819412231},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.558508038520813},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5562164187431335},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5120623707771301},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4671119451522827},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.4577741324901581},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4547429084777832},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41071611642837524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3013785183429718},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2806416.2806467","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2806416.2806467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:jupiter.its.unimelb.edu.au:11343/58271","is_oa":true,"landing_page_url":"http://hdl.handle.net/11343/58271","pdf_url":"http://hdl.handle.net/11343/58271","source":{"id":"https://openalex.org/S4377196259","display_name":"Minerva Access (University of Melbourne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165779595","host_organization_name":"The University of Melbourne","host_organization_lineage":["https://openalex.org/I165779595"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"24th ACM International on Conference on Information and Knowledge Management (CIKM)","raw_type":"Conference Paper"},{"id":"pmh:oai:alma.61RMIT_INST:11247911710001341","is_oa":false,"landing_page_url":"http://doi.org/10.1145/2806416.2806467","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/27392010","is_oa":true,"landing_page_url":null,"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":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:jupiter.its.unimelb.edu.au:11343/58271","is_oa":true,"landing_page_url":"http://hdl.handle.net/11343/58271","pdf_url":"http://hdl.handle.net/11343/58271","source":{"id":"https://openalex.org/S4377196259","display_name":"Minerva Access (University of Melbourne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165779595","host_organization_name":"The University of Melbourne","host_organization_lineage":["https://openalex.org/I165779595"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"24th ACM International on Conference on Information and Knowledge Management (CIKM)","raw_type":"Conference Paper"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8939304003","display_name":null,"funder_award_id":"DP140101587","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2048102545.pdf","grobid_xml":"https://content.openalex.org/works/W2048102545.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W192438917","https://openalex.org/W1545369573","https://openalex.org/W1583295779","https://openalex.org/W1584247327","https://openalex.org/W1605873790","https://openalex.org/W1858013062","https://openalex.org/W1953655781","https://openalex.org/W1964076997","https://openalex.org/W2015441003","https://openalex.org/W2022871093","https://openalex.org/W2046874737","https://openalex.org/W2070507812","https://openalex.org/W2070740689","https://openalex.org/W2087663869","https://openalex.org/W2114006712","https://openalex.org/W2119953525","https://openalex.org/W2120264533","https://openalex.org/W2151361488","https://openalex.org/W2155926818","https://openalex.org/W2162432120","https://openalex.org/W2165718308","https://openalex.org/W2166001746","https://openalex.org/W2263798363","https://openalex.org/W6635006130"],"related_works":["https://openalex.org/W1601713026","https://openalex.org/W2368542989","https://openalex.org/W2099421013","https://openalex.org/W2407111606","https://openalex.org/W2174009562","https://openalex.org/W2349125667","https://openalex.org/W2343034896","https://openalex.org/W50774052","https://openalex.org/W2335663899","https://openalex.org/W2740772059"],"abstract_inverted_index":{"Sophisticated":[0],"ranking":[1],"mechanisms":[2],"make":[3],"use":[4],"of":[5,86,98,110,128,132,150,187],"term":[6,25,100,152],"dependency":[7],"features":[8,18],"in":[9,126,159,166],"order":[10],"to":[11,48,51,62,115,181],"compute":[12,63,116,144],"similarity":[13,136],"scores":[14],"for":[15,147],"documents.":[16],"These":[17],"often":[19],"include":[20],"exact":[21],"phrase":[22],"occurrences,":[23],"and":[24,76],"proximity":[26,117,145],"estimates.":[27],"Both":[28],"cases":[29],"build":[30],"on":[31,103],"the":[32,43,52,59,83,87,140,175,188],"intuition":[33],"that":[34,168],"if":[35,177],"multiple":[36],"query":[37,133],"terms":[38,127],"appear":[39],"near":[40],"each":[41,93,178],"other,":[42],"document":[44,94],"is":[45,169],"more":[46],"likely":[47],"be":[49,71,113,174,182],"relevant":[50],"query.":[53],"In":[54],"this":[55],"paper":[56],"we":[57],"examine":[58],"processes":[60],"used":[61,72,114],"these":[64,104,121],"statistics.":[65,118],"Two":[66],"distinct":[67],"input":[68,106],"structures":[69],"can":[70,112],"--":[73],"inverted":[74],"files":[75,80,91],"direct":[77],"files.":[78],"Inverted":[79],"must":[81],"store":[82],"position":[84],"offsets":[85],"terms,":[88],"while":[89],"\"direct\"":[90],"represent":[92],"as":[95,139],"a":[96,108,129,148,156,194],"sequence":[97],"preprocessed":[99],"identifiers.":[101],"Based":[102],"two":[105],"modalities,":[107],"number":[109],"algorithms":[111,122],"Until":[119],"now,":[120],"have":[123],"been":[124],"described":[125],"single":[130],"set":[131],"terms.":[134],"But":[135],"computations":[137],"such":[138,161],"Full":[141],"Dependency":[142],"Model":[143],"statistics":[146],"collection":[149],"related":[151],"sets.":[153],"We":[154],"present":[155],"new":[157,189],"approach":[158],"which":[160],"collections":[162],"are":[163,191],"processed":[164],"holistically":[165],"time":[167],"much":[170],"less":[171],"than":[172],"would":[173],"case":[176],"subquery":[179],"were":[180],"evaluated":[183],"independently.":[184],"The":[185],"benefits":[186],"method":[190],"demonstrated":[192],"by":[193],"comprehensive":[195],"experimental":[196],"study.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}