{"id":"https://openalex.org/W2582619910","doi":"https://doi.org/10.17877/de290r-17781","title":"Automatic methods to extract latent meanings in large text corpora","display_name":"Automatic methods to extract latent meanings in large text corpora","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2582619910","doi":"https://doi.org/10.17877/de290r-17781","mag":"2582619910"},"language":"en","primary_location":{"id":"pmh:oai:eldorado.tu-dortmund.de:2003/35753","is_oa":false,"landing_page_url":"http://hdl.handle.net/2003/35753","pdf_url":null,"source":{"id":"https://openalex.org/S4306400811","display_name":"Technische Universit\u00e4t Dortmund Eldorado (Technische Universit\u00e4t Dortmund)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210148506","host_organization_name":"Erich-Brost-Institut","host_organization_lineage":["https://openalex.org/I4210148506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:doctoralThesis"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.17877/de290r-17781","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000254667","display_name":"Christian P\u00f6litz","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"P\u00f6litz, Christian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5000254667"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9776999950408936,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9776999950408936,"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":0.9474999904632568,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9204000234603882,"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/natural-language-processing","display_name":"Natural language processing","score":0.6132347583770752},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5632895231246948},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5393381714820862},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.436527281999588},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.14250025153160095}],"concepts":[{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6132347583770752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5632895231246948},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5393381714820862},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.436527281999588},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.14250025153160095}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:eldorado.tu-dortmund.de:2003/35753","is_oa":false,"landing_page_url":"http://hdl.handle.net/2003/35753","pdf_url":null,"source":{"id":"https://openalex.org/S4306400811","display_name":"Technische Universit\u00e4t Dortmund Eldorado (Technische Universit\u00e4t Dortmund)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210148506","host_organization_name":"Erich-Brost-Institut","host_organization_lineage":["https://openalex.org/I4210148506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:doctoralThesis"},{"id":"doi:10.17877/de290r-17781","is_oa":true,"landing_page_url":"https://doi.org/10.17877/de290r-17781","pdf_url":null,"source":{"id":"https://openalex.org/S4306400811","display_name":"Technische Universit\u00e4t Dortmund Eldorado (Technische Universit\u00e4t Dortmund)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210148506","host_organization_name":"Erich-Brost-Institut","host_organization_lineage":["https://openalex.org/I4210148506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"mag:2582619910","is_oa":false,"landing_page_url":"https://eldorado.tu-dortmund.de/handle/2003/35753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.17877/de290r-17781","is_oa":true,"landing_page_url":"https://doi.org/10.17877/de290r-17781","pdf_url":null,"source":{"id":"https://openalex.org/S4306400811","display_name":"Technische Universit\u00e4t Dortmund Eldorado (Technische Universit\u00e4t Dortmund)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210148506","host_organization_name":"Erich-Brost-Institut","host_organization_lineage":["https://openalex.org/I4210148506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2989969246","https://openalex.org/W3180117439","https://openalex.org/W3160100814","https://openalex.org/W38167433","https://openalex.org/W2900382651","https://openalex.org/W2115983295","https://openalex.org/W2581567250","https://openalex.org/W2571735341","https://openalex.org/W1598723751","https://openalex.org/W2808997405","https://openalex.org/W2888163711","https://openalex.org/W2602938991","https://openalex.org/W2885175469","https://openalex.org/W1980800232","https://openalex.org/W2544196827","https://openalex.org/W3012488131","https://openalex.org/W3149097876","https://openalex.org/W2997338223","https://openalex.org/W2505667296","https://openalex.org/W102233799"],"abstract_inverted_index":{"This":[0,141],"thesis":[1,563],"concentrates":[2],"on":[3,187,198,235,245,356,386,389,599],"Data":[4,15,549],"Mining":[5,16,550],"in":[6,27,30,101,121,138,201,375,469,609,632],"Corpus":[7,28],"Linguistic.":[8],"We":[9,125,177,265,589],"show":[10,126,275,506,626],"the":[11,31,70,76,79,95,111,173,227,239,247,276,280,302,305,322,337,349,361,370,373,387,395,409,429,432,446,467,470,487,529,532,548,559,562,569,575,579,584,595,600,606,610,617,620,627],"use":[12,112,281,483,601],"of":[13,33,56,60,75,94,113,134,145,224,282,304,324,339,360,372,377,445,531,605,619,629],"modern":[14,422,611],"by":[17,44,210,221,260],"developing":[18],"efficient":[19,507],"and":[20,25,35,48,103,136,166,205,238,271,278,358,380,474,495,537,572,583,636],"effective":[21],"methods":[22,116,148,268,285,291,296,308,314,327,333,342,354,367,398,491,560,582,586,608],"for":[23,149,182,269,286,343,431,492,547],"research":[24,494,635],"teaching":[26],"Linguistics":[29],"fields":[32],"lexicography":[34,102],"semantics.":[36],"Modern":[37],"language":[38,423,570,612],"resources":[39,59,571,613],"as":[40,399,545,553],"they":[41],"are":[42,81,163,169,208,215,242,254,292,297,315,452,500,587],"provided":[43],"Common":[45],"Language":[46],"Resources":[47],"Technology":[49],"Infrastructure":[50],"(http://clarin.eu)":[51],"offer":[52,91],"a":[53,202,418,421,436,542],"large":[54,64,106,122,150],"number":[55],"heterogeneous":[57],"information":[58,68,84,93,347,416,465,527,592],"written":[61],"language.":[62],"Besides":[63,351],"text":[65,107,123,139,573,576],"corpora,":[66,108,574],"additional":[67,415,441],"about":[69,85,348,417,466,528,593],"sources":[71,530],"or":[72,89,459,616],"publication":[73],"date":[74],"documents":[77,191,468,533],"from":[78,87,420,478,520,561],"corpora":[80,151,344],"available.":[82],"Further,":[83],"words":[86,135],"dictionaries":[88],"WordNets":[90],"prior":[92],"word":[96],"distributions.":[97],"Starting":[98],"with":[99,105,345,435,464,476,517],"pre-studies":[100,473],"semantics":[104],"we":[109,189,330,365,393,425,481,505,525],"investigate":[110,486],"latent":[114,146,160,174,183,206,219,240,258,283,306,325,340,390,396,404,433,448,457,462,489,509,515,580],"variable":[115,147,161,175,184,207,284,307,326,341,391,397,449,490,581],"to":[117,132,152,171,217,256,299,309,317,320,334,368,406,427,454,485,512,534,557,568,625],"extract":[118,218,257],"hidden":[119,129,363],"concepts":[120,130,374],"collections.":[124,140],"that":[127,382,402,438],"these":[128],"correspond":[131],"meanings":[133],"subjects":[137],"motivates":[142],"an":[143,157],"investigation":[144],"support":[153],"linguistic":[154,493,634],"research.":[155],"In":[156,443,502,522],"extensive":[158],"survey,":[159],"models":[162,185,214,253,511],"described.":[164,565],"Mathematical":[165],"geometrical":[167],"foundations":[168],"explained":[170,624],"motivate":[172],"methods.":[176],"distinguish":[178],"two":[179],"starting":[180],"points":[181],"depending":[186,263],"how":[188,319,594],"represent":[190],"internally.":[192],"The":[193,230,566,603],"first":[194],"representation":[195,232],"is":[196,233,555,564,597,623],"based":[197,234,355],"geometric":[199],"objects":[200],"vector":[203],"space":[204],"represented":[209],"vectors.":[211],"Latent":[212,251],"factor":[213,270],"described":[216,255,298],"variables":[220,241,244,259,405,434,516],"finding":[222,261],"factorizations":[223],"matrices":[225],"summarizing":[226],"document":[228,410],"objects.":[229],"second":[231],"random":[236,243],"sequences":[237,248],"which":[246],"conditionally":[249,262],"depend.":[250],"topic":[252,272,510],"variables.":[264],"explain":[266],"state-of-the-art":[267],"models.":[273],"To":[274,412],"quality":[277,323,338],"hence":[279],"corpus":[287,419,479,633],"linguistic,":[288],"different":[289,447],"evaluation":[290,295,313,353,585],"discussed.":[293],"Qualitative":[294],"effectively":[300],"present":[301],"results":[303],"users.":[310],"State-of-the-art":[311],"quantitative":[312],"summarized":[316],"illustrate":[318],"measure":[321],"automatically.":[328],"Additional,":[329],"propose":[331,426],"new":[332],"efficiently":[335,413],"estimate":[336,369],"time":[346,518],"documents.":[350,521],"standard":[352],"likelihoods":[357,381],"coherences":[359],"extracted":[362],"concepts,":[364],"develop":[366],"coherence":[371],"terms":[376,444],"temporal":[378],"aspects":[379],"including":[383],"time.":[384],"Based":[385],"survey":[388],"methods,":[392,578],"interpret":[394],"optimization":[400,430],"problem":[401],"finds":[403],"optimally":[407],"describe":[408],"corpus.":[411,471],"integrate":[414,526],"resources,":[424],"extend":[428],"regularization":[437],"includes":[439],"this":[440],"information.":[442],"models,":[450],"regularizations":[451],"proposed":[453],"either":[455],"align":[456],"factors":[458],"jointly":[460,513],"model":[461,514,535],"topics":[463],"From":[472],"collaborations":[475],"researches":[477],"linguistics,":[480,504,524],"compiled":[482],"cases":[484],"regularized":[488,508],"teaching.":[496,637],"Two":[497],"major":[498],"application":[499],"investigated.":[501],"diachronic":[503],"stamps":[519],"variety":[523],"similarities":[536],"dissimilarities":[538],"between":[539],"corpora.":[540],"Finally,":[541],"software":[543,596],"package":[544],"Plugin":[546],"toolkit":[551],"RapidMiner":[552],"it":[554],"developed":[556,607],"implement":[558],"interfaces":[567],"processing":[577],"specified.":[588],"give":[590],"detailed":[591],"used":[598],"cases.":[602],"integration":[604],"like":[614],"WebLicht":[615],"Dictionary":[618],"German":[621],"Languages":[622],"acceptance":[628],"our":[630],"method":[631]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}