{"id":"https://openalex.org/W2122557596","doi":"https://doi.org/10.1109/ijcnn.2004.1380163","title":"Pruning the vocabulary for better context recognition","display_name":"Pruning the vocabulary for better context recognition","publication_year":2005,"publication_date":"2005-04-05","ids":{"openalex":"https://openalex.org/W2122557596","doi":"https://doi.org/10.1109/ijcnn.2004.1380163","mag":"2122557596"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2004.1380163","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2004.1380163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)","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/A5049279492","display_name":"Rasmus Elsborg Madsen","orcid":null},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"R.E. Madsen","raw_affiliation_strings":["Informatics and Mathematical Modelling, Technical University of Denmark, Kongens Lyngby, Denmark","#N##TAB##TAB##TAB##TAB# Technical University of Denmark#N##TAB##TAB##TAB#"],"affiliations":[{"raw_affiliation_string":"Informatics and Mathematical Modelling, Technical University of Denmark, Kongens Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]},{"raw_affiliation_string":"#N##TAB##TAB##TAB##TAB# Technical University of Denmark#N##TAB##TAB##TAB#","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091163773","display_name":"Sn\u00e6var Sigur\u00f0sson","orcid":"https://orcid.org/0000-0003-4860-6311"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"S. Sigurdsson","raw_affiliation_strings":["Informatics and Mathematical Modelling, Technical University of Denmark, Kongens Lyngby, Denmark","#N##TAB##TAB##TAB##TAB# Technical University of Denmark#N##TAB##TAB##TAB#"],"affiliations":[{"raw_affiliation_string":"Informatics and Mathematical Modelling, Technical University of Denmark, Kongens Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]},{"raw_affiliation_string":"#N##TAB##TAB##TAB##TAB# Technical University of Denmark#N##TAB##TAB##TAB#","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018292103","display_name":"Lars Kai Hansen","orcid":"https://orcid.org/0000-0003-0442-5877"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Lars Kai Hansen","raw_affiliation_strings":["Informatics and Mathematical Modelling, Technical University of Denmark, Kongens Lyngby, Denmark"],"affiliations":[{"raw_affiliation_string":"Informatics and Mathematical Modelling, Technical University of Denmark, Kongens Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089509071","display_name":"Jakob Eg Larsen","orcid":"https://orcid.org/0000-0002-7461-9901"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"J. Larsen","raw_affiliation_strings":["Informatics and Mathematical Modelling, Technical University of Denmark, Kongens Lyngby, Denmark","#N##TAB##TAB##TAB##TAB# Technical University of Denmark#N##TAB##TAB##TAB#"],"affiliations":[{"raw_affiliation_string":"Informatics and Mathematical Modelling, Technical University of Denmark, Kongens Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]},{"raw_affiliation_string":"#N##TAB##TAB##TAB##TAB# Technical University of Denmark#N##TAB##TAB##TAB#","institution_ids":["https://openalex.org/I96673099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5049279492"],"corresponding_institution_ids":["https://openalex.org/I96673099"],"apc_list":null,"apc_paid":null,"fwci":0.4388,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.74623424,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"1439","last_page":"1444"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998000264167786,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9998000264167786,"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":0.9976000189781189,"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":0.9968000054359436,"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":0.7723930478096008},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7351721525192261},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5880292654037476},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5777878165245056},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5685390830039978},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5504964590072632},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.531121015548706},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.48469188809394836},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4524194598197937},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4377742111682892},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.4258931875228882},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3858132064342499},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36555707454681396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7723930478096008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7351721525192261},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5880292654037476},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5777878165245056},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5685390830039978},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5504964590072632},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.531121015548706},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.48469188809394836},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4524194598197937},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4377742111682892},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.4258931875228882},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3858132064342499},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36555707454681396},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2004.1380163","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2004.1380163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W116908793","https://openalex.org/W206499635","https://openalex.org/W1504118426","https://openalex.org/W1508647450","https://openalex.org/W1578881253","https://openalex.org/W1600320866","https://openalex.org/W1663369658","https://openalex.org/W1870755964","https://openalex.org/W1989568037","https://openalex.org/W1989993068","https://openalex.org/W1991629007","https://openalex.org/W1995001633","https://openalex.org/W2007278710","https://openalex.org/W2025472057","https://openalex.org/W2035411645","https://openalex.org/W2064450304","https://openalex.org/W2105948726","https://openalex.org/W2118020653","https://openalex.org/W2139578439","https://openalex.org/W2147152072","https://openalex.org/W2435251607","https://openalex.org/W2541290235","https://openalex.org/W2951911250","https://openalex.org/W3152443087","https://openalex.org/W4231923904","https://openalex.org/W4239696231","https://openalex.org/W4245049592","https://openalex.org/W6604700743","https://openalex.org/W6608504534","https://openalex.org/W6630523288","https://openalex.org/W6639241423","https://openalex.org/W6680380971","https://openalex.org/W6717827561"],"related_works":["https://openalex.org/W2365213443","https://openalex.org/W2547327959","https://openalex.org/W2375851949","https://openalex.org/W2563096758","https://openalex.org/W37985898","https://openalex.org/W2373148153","https://openalex.org/W4386053843","https://openalex.org/W3158004940","https://openalex.org/W2094694265","https://openalex.org/W2543958478"],"abstract_inverted_index":{"Language":[0],"independent":[1],"'bag-of-words'":[2],"representations":[3],"are":[4,87],"surprisingly":[5],"effective":[6],"for":[7,20,74,128],"text":[8,21],"classification.":[9],"The":[10],"representation":[11,94],"is":[12,45],"high":[13],"dimensional":[14],"though,":[15],"containing":[16],"many":[17],"non-consistent":[18,24],"words":[19,25,55],"categorization.":[22],"These":[23],"result":[26],"in":[27],"reduced":[28,84],"generalization":[29],"performance":[30],"of":[31,50,76,122],"subsequent":[32],"classifiers,":[33],"e.g.,":[34],"from":[35,56],"ill-posed":[36],"principal":[37],"component":[38],"transformations.":[39],"In":[40],"this":[41],"communication,":[42],"our":[43],"aim":[44],"to":[46],"study":[47,119],"the":[48,52,57,81,102,120],"effect":[49],"reducing":[51],"least":[53],"relevant":[54],"bag-of-words":[58,103],"representation.":[59],"We":[60,117],"consider":[61],"a":[62,90,96],"new":[63],"approach,":[64],"using":[65,89,112],"neural":[66,98],"network":[67,99],"based":[68],"sensitivity":[69,126],"maps":[70,127],"and":[71,95,125],"information":[72,123],"gain":[73,124],"determination":[75],"term":[77],"relevancy,":[78],"when":[79],"pruning":[80],"vocabularies.":[82],"With":[83],"vocabularies,":[85],"documents":[86],"classified":[88],"latent":[91],"semantic":[92],"indexing":[93],"probabilistic":[97],"classifier.":[100],"Reducing":[101],"vocabularies":[104],"with":[105],"90%-98%,":[106],"we":[107],"find":[108],"consistent":[109],"classification":[110],"improvement":[111],"two":[113],"mid":[114],"size":[115],"data-sets.":[116],"also":[118],"applicability":[121],"automated":[129],"keyword":[130],"generation.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}