{"id":"https://openalex.org/W3094022303","doi":"https://doi.org/10.1145/3340531.3412773","title":"Feature Extraction for Large-Scale Text Collections","display_name":"Feature Extraction for Large-Scale Text Collections","publication_year":2020,"publication_date":"2020-10-19","ids":{"openalex":"https://openalex.org/W3094022303","doi":"https://doi.org/10.1145/3340531.3412773","mag":"3094022303"},"language":"en","primary_location":{"id":"doi:10.1145/3340531.3412773","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340531.3412773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072101832","display_name":"Luke Gallagher","orcid":"https://orcid.org/0000-0002-3241-7615"},"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":"Luke Gallagher","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/A5004258130","display_name":"Antonio Mallia","orcid":"https://orcid.org/0000-0002-7817-6140"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonio Mallia","raw_affiliation_strings":["New York University, New York, Italy"],"affiliations":[{"raw_affiliation_string":"New York University, New York, Italy","institution_ids":["https://openalex.org/I57206974"]}]},{"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, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074323303","display_name":"Torsten Suel","orcid":"https://orcid.org/0000-0002-8324-980X"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Torsten Suel","raw_affiliation_strings":["New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015615642","display_name":"B. Barla Cambazo\u011flu","orcid":"https://orcid.org/0000-0003-2192-3819"},"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":"B. Barla Cambazoglu","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":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5072101832"],"corresponding_institution_ids":["https://openalex.org/I82951845"],"apc_list":null,"apc_paid":null,"fwci":0.2782,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67194756,"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":"3015","last_page":"3022"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9984999895095825,"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":0.9984999895095825,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9976999759674072,"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/T10028","display_name":"Topic Modeling","score":0.9973999857902527,"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":0.7914475202560425},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6157000064849854},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5699447393417358},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5585560202598572},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5532059669494629},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.49509158730506897},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.4938972592353821},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.47858262062072754},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.47371119260787964},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.47070547938346863},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4612729549407959},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.45614832639694214},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.4323852062225342},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.4234405755996704},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2694806456565857},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.20406699180603027},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.19040849804878235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7914475202560425},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6157000064849854},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5699447393417358},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5585560202598572},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5532059669494629},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.49509158730506897},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.4938972592353821},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.47858262062072754},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.47371119260787964},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.47070547938346863},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4612729549407959},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.45614832639694214},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.4323852062225342},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.4234405755996704},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2694806456565857},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.20406699180603027},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.19040849804878235},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3340531.3412773","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340531.3412773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.61RMIT_INST:11272963960001341","is_oa":false,"landing_page_url":"http://purl.org/au-research/grants/arc/DP190101113","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/27589029","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:figshare.com:article/27589029","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"},"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W69540849","https://openalex.org/W1678356000","https://openalex.org/W1791987072","https://openalex.org/W1993924397","https://openalex.org/W1999322447","https://openalex.org/W2000431947","https://openalex.org/W2024463435","https://openalex.org/W2048102545","https://openalex.org/W2053448995","https://openalex.org/W2070740689","https://openalex.org/W2077789969","https://openalex.org/W2105380208","https://openalex.org/W2114690085","https://openalex.org/W2124504084","https://openalex.org/W2149427297","https://openalex.org/W2155482025","https://openalex.org/W2155926818","https://openalex.org/W2243869100","https://openalex.org/W2307814545","https://openalex.org/W2469056188","https://openalex.org/W2470088391","https://openalex.org/W2531355666","https://openalex.org/W2590822507","https://openalex.org/W2609826708","https://openalex.org/W2610935556","https://openalex.org/W2741632195","https://openalex.org/W2758508602","https://openalex.org/W2784672094","https://openalex.org/W2799232306","https://openalex.org/W2884475480","https://openalex.org/W2889787757","https://openalex.org/W2899154813","https://openalex.org/W2902671359","https://openalex.org/W2908332126","https://openalex.org/W2949868354","https://openalex.org/W2954217339","https://openalex.org/W2962985038","https://openalex.org/W3009633639","https://openalex.org/W3034521898","https://openalex.org/W3088653102","https://openalex.org/W3102704970","https://openalex.org/W4252076394","https://openalex.org/W4300762054","https://openalex.org/W6600757733","https://openalex.org/W6747597888"],"related_works":["https://openalex.org/W2131958170","https://openalex.org/W2061122711","https://openalex.org/W2273754158","https://openalex.org/W4247954915","https://openalex.org/W2336747664","https://openalex.org/W2772359885","https://openalex.org/W3011471740","https://openalex.org/W4379381520","https://openalex.org/W2884580467","https://openalex.org/W2572315477"],"abstract_inverted_index":{"Feature":[0],"engineering":[1],"is":[2,40],"a":[3,41,113],"fundamental":[4],"but":[5],"poorly":[6],"documented":[7],"component":[8],"in":[9,44,119],"Learning-to-Rank":[10],"(LTR)":[11],"search":[12,27,114],"engines.":[13],"Such":[14],"features":[15,69,129],"are":[16,57,105,124],"commonly":[17],"used":[18],"to":[19,107,137],"construct":[20],"learning":[21,68],"models":[22],"for":[23,134],"web":[24],"and":[25,31,110],"product":[26],"engines,":[28],"recommender":[29],"systems,":[30],"question-answering":[32],"tasks.":[33],"In":[34],"each":[35],"of":[36,47,64,98,103,112],"these":[37,104],"domains,":[38],"there":[39,56],"growing":[42],"interest":[43],"the":[45,92,99,122],"creation":[46,109],"open-access":[48],"test":[49,82],"collections":[50],"that":[51],"promote":[52],"reproducible":[53,126],"research.":[54],"However,":[55],"still":[58],"few":[59],"open-source":[60],"software":[61],"packages":[62],"capable":[63],"extracting":[65],"high-quality":[66],"machine":[67],"from":[70],"large":[71],"text":[72],"collections.":[73],"Instead,":[74],"most":[75],"feature-based":[76],"LTR":[77,139],"research":[78],"relies":[79],"on":[80],"\"canned\"":[81],"collections,":[83,131],"which":[84],"often":[85],"do":[86],"not":[87],"expose":[88],"critical":[89],"details":[90,97],"about":[91],"underlying":[93],"collection":[94,108],"or":[95,130,132],"implementation":[96],"extracted":[100],"features.":[101],"Both":[102],"crucial":[106],"deployment":[111],"engine":[115],"into":[116],"production.":[117],"So":[118],"this":[120],"regard,":[121],"experiments":[123],"rarely":[125],"with":[127],"new":[128],"helpful":[133],"companies":[135],"wishing":[136],"deploy":[138],"systems.":[140]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}