{"id":"https://openalex.org/W2252108544","doi":"https://doi.org/10.3115/v1/w15-1505","title":"Distributional Representations of Words for Short Text Classification","display_name":"Distributional Representations of Words for Short Text Classification","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2252108544","doi":"https://doi.org/10.3115/v1/w15-1505","mag":"2252108544"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w15-1505","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w15-1505","pdf_url":"https://www.aclweb.org/anthology/W15-1505.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W15-1505.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101539986","display_name":"Chenglong Ma","orcid":"https://orcid.org/0000-0002-1632-2480"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Ma","raw_affiliation_strings":["The Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics, Chinese Academy of Sciences No. 21 North 4th Ring West Road, Haidian District, 100190 Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics, Chinese Academy of Sciences No. 21 North 4th Ring West Road, Haidian District, 100190 Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101544773","display_name":"Weiqun Xu","orcid":"https://orcid.org/0000-0002-6654-3572"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiqun Xu","raw_affiliation_strings":["The Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics, Chinese Academy of Sciences No. 21 North 4th Ring West Road, Haidian District, 100190 Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics, Chinese Academy of Sciences No. 21 North 4th Ring West Road, Haidian District, 100190 Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102772761","display_name":"Peijia Li","orcid":"https://orcid.org/0000-0003-2989-8777"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peijia Li","raw_affiliation_strings":["The Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics, Chinese Academy of Sciences No. 21 North 4th Ring West Road, Haidian District, 100190 Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics, Chinese Academy of Sciences No. 21 North 4th Ring West Road, Haidian District, 100190 Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100425112","display_name":"Yonghong Yan","orcid":"https://orcid.org/0000-0001-6907-5770"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Yan","raw_affiliation_strings":["The Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics, Chinese Academy of Sciences No. 21 North 4th Ring West Road, Haidian District, 100190 Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics, Chinese Academy of Sciences No. 21 North 4th Ring West Road, Haidian District, 100190 Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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":0.9933000206947327,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9915000200271606,"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/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.8173476457595825},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7250767946243286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7188623547554016},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.6684855818748474},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5644415020942688},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5514501333236694},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5189864039421082},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4777097702026367},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.45375749468803406},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.45045146346092224},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.43085020780563354},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4189056158065796},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4126822352409363},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.40376198291778564},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38673609495162964},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16886669397354126}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.8173476457595825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7250767946243286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7188623547554016},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.6684855818748474},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5644415020942688},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5514501333236694},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5189864039421082},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4777097702026367},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.45375749468803406},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.45045146346092224},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.43085020780563354},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4189056158065796},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4126822352409363},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.40376198291778564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38673609495162964},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16886669397354126},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/v1/w15-1505","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w15-1505","pdf_url":"https://www.aclweb.org/anthology/W15-1505.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/v1/w15-1505","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w15-1505","pdf_url":"https://www.aclweb.org/anthology/W15-1505.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.6299999952316284,"display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G2642921961","display_name":null,"funder_award_id":"91120001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3521891072","display_name":null,"funder_award_id":"XDA06030500","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"id":"https://openalex.org/G4243412236","display_name":null,"funder_award_id":"863 Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6258617591","display_name":null,"funder_award_id":"XDA06030100","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"id":"https://openalex.org/G6657427635","display_name":"\u8bed\u97f3\u7f3a\u5931\u9891\u8c31\u91cd\u5efa\u53ca\u8bed\u97f3\u9891\u8c31\u4e8c\u7ef4\u76f8\u5173\u6027\u5efa\u6a21\u7684\u7814\u7a76","funder_award_id":"61271426","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8597161911","display_name":null,"funder_award_id":"KGZD-EW-103-2","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"id":"https://openalex.org/G985889194","display_name":null,"funder_award_id":"11161140319","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320335773","display_name":"National High-tech Research and Development Program","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2252108544.pdf","grobid_xml":"https://content.openalex.org/works/W2252108544.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W27263903","https://openalex.org/W1553682320","https://openalex.org/W1573190978","https://openalex.org/W1833785989","https://openalex.org/W1880262756","https://openalex.org/W2055400882","https://openalex.org/W2064580901","https://openalex.org/W2088314245","https://openalex.org/W2130284530","https://openalex.org/W2141599568","https://openalex.org/W2149393279","https://openalex.org/W2153579005","https://openalex.org/W2158139315","https://openalex.org/W2158899491","https://openalex.org/W2171836785","https://openalex.org/W2250434988","https://openalex.org/W2250521169","https://openalex.org/W2952230511","https://openalex.org/W4231510805","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2888805565","https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W3159709618","https://openalex.org/W2497860580","https://openalex.org/W2891616219","https://openalex.org/W3204672119"],"abstract_inverted_index":{"Traditional":[0],"supervised":[1],"learning":[2],"approaches":[3],"to":[4,32,88],"common":[5],"NLP":[6],"tasks":[7],"depend":[8],"heavily":[9],"on":[10,116],"manual":[11],"annotation,":[12],"which":[13],"is":[14,71,86,111],"labor":[15],"intensive":[16],"and":[17,20,123,135],"time":[18],"consuming,":[19],"often":[21],"suffer":[22],"from":[23,49,58],"data":[24],"sparseness.":[25],"In":[26],"this":[27],"paper":[28],"we":[29],"show":[30],"how":[31],"mitigate":[33],"the":[34,59,90,104,117,124],"problems":[35],"in":[36,78,139],"short":[37,68],"text":[38,69],"classification":[39,97],"(STC)":[40],"through":[41],"word":[42,54],"embeddings":[43,55],"-distributional":[44],"representations":[45],"of":[46,75,92,96,102],"words":[47],"learned":[48],"large":[50],"unlabeled":[51],"data.":[52],"The":[53,94],"are":[56],"trained":[57],"entire":[60],"English":[61],"Wikipedia":[62],"text.":[63],"We":[64],"assume":[65],"that":[66],"a":[67,72,79,99],"document":[70],"specific":[73],"sample":[74],"one":[76],"distribution":[77,91],"Bayesian":[80],"framework.":[81],"A":[82],"Gaussian":[83,107],"process":[84],"approach":[85,110,131],"used":[87],"model":[89,122],"words.":[93,143],"task":[95],"becomes":[98],"simple":[100],"problem":[101],"selecting":[103],"most":[105],"probable":[106],"distribution.":[108],"This":[109],"compared":[112],"with":[113,141],"those":[114],"based":[115],"classical":[118],"maximum":[119],"entropy":[120],"(MaxEnt)":[121],"Latent":[125],"Dirichlet":[126],"Allocation":[127],"(LDA)":[128],"approach.":[129],"Our":[130],"achieved":[132],"better":[133],"performance":[134],"also":[136],"showed":[137],"advantages":[138],"dealing":[140],"unseen":[142]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}