{"id":"https://openalex.org/W2949751989","doi":"https://doi.org/10.18653/v1/p19-1036","title":"Towards Unsupervised Text Classification Leveraging Experts and Word Embeddings","display_name":"Towards Unsupervised Text Classification Leveraging Experts and Word Embeddings","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2949751989","doi":"https://doi.org/10.18653/v1/p19-1036","mag":"2949751989"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1036","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1036","pdf_url":"https://www.aclweb.org/anthology/P19-1036.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1036.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076865270","display_name":"Zied Haj-Yahia","orcid":null},"institutions":[{"id":"https://openalex.org/I18850439","display_name":"Capgemini (Netherlands)","ror":"https://ror.org/03amxdk57","country_code":"NL","type":"company","lineage":["https://openalex.org/I18850439","https://openalex.org/I4210136798"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Zied Haj-Yahia","raw_affiliation_strings":["Capgemini Invent"],"affiliations":[{"raw_affiliation_string":"Capgemini Invent","institution_ids":["https://openalex.org/I18850439"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086942921","display_name":"Adrien Sieg","orcid":null},"institutions":[{"id":"https://openalex.org/I18850439","display_name":"Capgemini (Netherlands)","ror":"https://ror.org/03amxdk57","country_code":"NL","type":"company","lineage":["https://openalex.org/I18850439","https://openalex.org/I4210136798"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Adrien Sieg","raw_affiliation_strings":["Capgemini Invent"],"affiliations":[{"raw_affiliation_string":"Capgemini Invent","institution_ids":["https://openalex.org/I18850439"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043728661","display_name":"L\u00e9a A. Deleris","orcid":null},"institutions":[{"id":"https://openalex.org/I18850439","display_name":"Capgemini (Netherlands)","ror":"https://ror.org/03amxdk57","country_code":"NL","type":"company","lineage":["https://openalex.org/I18850439","https://openalex.org/I4210136798"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"L\u00e9a A. Deleris","raw_affiliation_strings":["Capgemini Invent"],"affiliations":[{"raw_affiliation_string":"Capgemini Invent","institution_ids":["https://openalex.org/I18850439"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076865270"],"corresponding_institution_ids":["https://openalex.org/I18850439"],"apc_list":null,"apc_paid":null,"fwci":3.1833,"has_fulltext":true,"cited_by_count":46,"citation_normalized_percentile":{"value":0.93583408,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"371","last_page":"379"},"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":0.9973999857902527,"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"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9930999875068665,"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":0.8384972214698792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7018597722053528},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6536426544189453},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.6242901682853699},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6147446036338806},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5555331707000732},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5533902645111084},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5198007822036743},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.48168596625328064},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.4676871597766876},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43606099486351013},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.430292546749115},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4265786409378052},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37310928106307983},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07883551716804504}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8384972214698792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7018597722053528},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6536426544189453},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.6242901682853699},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6147446036338806},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5555331707000732},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5533902645111084},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5198007822036743},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.48168596625328064},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.4676871597766876},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43606099486351013},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.430292546749115},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4265786409378052},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37310928106307983},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07883551716804504},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1036","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1036","pdf_url":"https://www.aclweb.org/anthology/P19-1036.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1036","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1036","pdf_url":"https://www.aclweb.org/anthology/P19-1036.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2949751989.pdf","grobid_xml":"https://content.openalex.org/works/W2949751989.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W33843741","https://openalex.org/W168564468","https://openalex.org/W1614298861","https://openalex.org/W1987054081","https://openalex.org/W2038043464","https://openalex.org/W2047760401","https://openalex.org/W2085256060","https://openalex.org/W2097089247","https://openalex.org/W2107008379","https://openalex.org/W2118020653","https://openalex.org/W2140679639","https://openalex.org/W2153579005","https://openalex.org/W2170240176","https://openalex.org/W2250539671","https://openalex.org/W2509601217","https://openalex.org/W2824731080","https://openalex.org/W2896457183","https://openalex.org/W2949998441","https://openalex.org/W2950577311","https://openalex.org/W2962739339","https://openalex.org/W2963012544","https://openalex.org/W2963341956","https://openalex.org/W3146306708","https://openalex.org/W4285719527","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2381242807","https://openalex.org/W3126131230","https://openalex.org/W2347541121","https://openalex.org/W2165912799","https://openalex.org/W4288804799","https://openalex.org/W2080951048","https://openalex.org/W3089617106","https://openalex.org/W3032237421","https://openalex.org/W2390346111","https://openalex.org/W2023946029"],"abstract_inverted_index":{"Text":[0],"classification":[1],"aims":[2],"at":[3],"mapping":[4],"documents":[5,31,63],"into":[6,64],"a":[7,26,69,79,99,126,171],"set":[8],"of":[9,29,43,101,114,121,128],"predefined":[10],"categories.":[11],"Supervised":[12],"machine":[13],"learning":[14],"models":[15],"have":[16],"shown":[17],"great":[18],"success":[19],"in":[20,47,82,95],"this":[21,54,83],"area":[22],"but":[23],"they":[24],"require":[25],"large":[27],"number":[28,42],"labeled":[30],"to":[32,61,174,188],"reach":[33],"adequate":[34],"accuracy.":[35],"This":[36],"is":[37,46,74,180],"particularly":[38],"true":[39],"when":[40],"the":[41,48,51,77,91,119,122,147],"target":[44],"categories":[45,65],"tens":[49],"or":[50],"hundreds.":[52],"In":[53],"work,":[55],"we":[56,183],"explore":[57],"an":[58],"unsupervised":[59],"approach":[60],"classify":[62],"simply":[66],"described":[67],"by":[68,76],"label.":[70],"The":[71,112],"proposed":[72,148],"method":[73,116,149],"inspired":[75],"way":[78],"human":[80,129,156],"proceeds":[81],"situation:":[84],"It":[85,168],"draws":[86],"on":[87,118,141,155,162],"textual":[88],"similarity":[89],"between":[90],"most":[92],"relevant":[93],"words":[94],"each":[96,104],"document":[97],"and":[98,109,131,136,158],"dictionary":[100],"keywords":[102],"for":[103],"category":[105,123],"reflecting":[106],"its":[107],"semantics":[108],"lexical":[110],"field.":[111],"novelty":[113],"our":[115,186],"hinges":[117],"enrichment":[120],"labels":[124],"through":[125],"combination":[127],"expertise":[130,157],"language":[132],"models,":[133],"both":[134],"generic":[135],"domain":[137],"specific.":[138],"Our":[139],"experiments":[140],"5":[142],"standard":[143],"corpora":[144],"show":[145],"that":[146],"increases":[150],"F1-score":[151],"over":[152],"relying":[153],"solely":[154],"can":[159],"also":[160],"be":[161],"par":[163],"with":[164,185],"simple":[165],"supervised":[166],"approaches.":[167],"thus":[169],"provides":[170],"practical":[172],"alternative":[173],"situations":[175],"where":[176],"lowcost":[177],"text":[178],"categorization":[179],"needed,":[181],"as":[182],"illustrate":[184],"application":[187],"operational":[189],"risk":[190],"incidents":[191],"classification.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}