{"id":"https://openalex.org/W4382201643","doi":"https://doi.org/10.1145/3582768.3582795","title":"Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based Approaches","display_name":"Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based Approaches","publication_year":2022,"publication_date":"2022-12-16","ids":{"openalex":"https://openalex.org/W4382201643","doi":"https://doi.org/10.1145/3582768.3582795"},"language":"en","primary_location":{"id":"doi:10.1145/3582768.3582795","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3582768.3582795","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5037301059","display_name":"Tim Schopf","orcid":"https://orcid.org/0000-0003-3849-0394"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tim Schopf","raw_affiliation_strings":["Department of Computer Science, Technical University of Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3849-0394","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036520551","display_name":"Daniel Braun","orcid":"https://orcid.org/0000-0001-8120-3368"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Daniel Braun","raw_affiliation_strings":["Department of High-tech Business and Entrepreneurship, University of Twente, Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-8120-3368","affiliations":[{"raw_affiliation_string":"Department of High-tech Business and Entrepreneurship, University of Twente, Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022973212","display_name":"Florian Matthes","orcid":"https://orcid.org/0000-0002-6667-5452"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Matthes","raw_affiliation_strings":["Department of Computer Science, Technical University of Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6667-5452","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.6019,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.9837865,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994000196456909,"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":0.9927999973297119,"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/similarity","display_name":"Similarity (geometry)","score":0.7331437468528748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7245064377784729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7026757001876831},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5691757798194885},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5152209401130676},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48765861988067627},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.4874275028705597},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4233074188232422},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39211905002593994},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34972357749938965},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14037269353866577}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7331437468528748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7245064377784729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7026757001876831},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5691757798194885},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5152209401130676},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48765861988067627},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.4874275028705597},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4233074188232422},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39211905002593994},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34972357749938965},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14037269353866577},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3582768.3582795","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3582768.3582795","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:ris.utwente.nl:openaire_cris_publications/7e4b4897-b917-420c-b64d-a51b88c4d26b","is_oa":false,"landing_page_url":"https://research.utwente.nl/en/publications/7e4b4897-b917-420c-b64d-a51b88c4d26b","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Schopf, T, Braun, D & Matthes, F 2022, Evaluating Unsupervised Text Classification: Zero-Shot and Similarity-Based Approaches. in Proceedings of the 2022 6th International Conference on Natural Language Processing and Information Retrieval. Association for Computing Machinery, New York, NY, USA, pp. 6\u201315, 6th International Conference on Natural Language Processing and Information Retrieval, NLPIR 2022, Bangkok, Thailand, 16/12/22. https://doi.org/10.1145/3582768.3582795","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"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":28,"referenced_works":["https://openalex.org/W1493526108","https://openalex.org/W2147152072","https://openalex.org/W2285986798","https://openalex.org/W2551773530","https://openalex.org/W2802787326","https://openalex.org/W2889577585","https://openalex.org/W2909182718","https://openalex.org/W2910453440","https://openalex.org/W2913059114","https://openalex.org/W2937423263","https://openalex.org/W2949751989","https://openalex.org/W2963804400","https://openalex.org/W2963846996","https://openalex.org/W2963961878","https://openalex.org/W3024119303","https://openalex.org/W3034608141","https://openalex.org/W3034999214","https://openalex.org/W3105625590","https://openalex.org/W3115913034","https://openalex.org/W3152936485","https://openalex.org/W3156333129","https://openalex.org/W3156636935","https://openalex.org/W3162305607","https://openalex.org/W3184365942","https://openalex.org/W3210032674","https://openalex.org/W4285815570","https://openalex.org/W4308045040","https://openalex.org/W4317035032"],"related_works":["https://openalex.org/W2375480909","https://openalex.org/W2353314428","https://openalex.org/W2012019886","https://openalex.org/W2166090428","https://openalex.org/W2381021552","https://openalex.org/W2354749003","https://openalex.org/W2377121353","https://openalex.org/W2350529538","https://openalex.org/W2366015234","https://openalex.org/W2354233396"],"abstract_inverted_index":{"Text":[0],"classification":[1,41,101,113,142,191],"of":[2,20,56,93,102,185],"unseen":[3,103],"classes":[4,58],"is":[5,13,154],"a":[6,49,80,90,116],"challenging":[7],"Natural":[8],"Language":[9],"Processing":[10],"task":[11,51],"and":[12,35,96,127,144],"mainly":[14],"attempted":[15],"using":[16,179],"two":[17],"different":[18,94],"types":[19],"approaches.":[21],"Similarity-based":[22],"approaches":[23,42,69,98,107,160,170,174],"attempt":[24],"to":[25,44,59,70],"classify":[26],"instances":[27],"based":[28],"on":[29,110],"similarities":[30],"between":[31],"text":[32,40,60,100,112,163,187],"document":[33],"representations":[34,188],"class":[36],"description":[37],"representations.":[38],"Zero-shot":[39],"aim":[43],"generalize":[45],"knowledge":[46],"gained":[47],"from":[48,119],"training":[50],"by":[52,88],"assigning":[53],"appropriate":[54],"labels":[55],"unknown":[57],"documents.":[61],"Although":[62],"existing":[63,138],"studies":[64],"have":[65],"already":[66],"investigated":[67],"individual":[68],"these":[71],"categories,":[72],"the":[73,120,149],"experiments":[74,166],"in":[75,137,161,175],"literature":[76],"do":[77],"not":[78],"provide":[79],"consistent":[81],"comparison.":[82],"This":[83],"paper":[84],"addresses":[85],"this":[86],"gap":[87],"conducting":[89],"systematic":[91],"evaluation":[92],"similarity-based":[95,151,169,190],"zero-shot":[97,173],"for":[99],"classes.":[104],"Different":[105],"state-of-the-art":[106,159],"are":[108,131,145],"benchmarked":[109],"four":[111],"datasets,":[114],"including":[115],"new":[117],"dataset":[118],"medical":[121],"domain.":[122],"Additionally,":[123,178],"novel":[124,150],"SimCSE":[125,180],"[7]":[126],"SBERT-based":[128],"[26]":[129],"baselines":[130,135],"proposed,":[132],"as":[133],"other":[134],"used":[136],"work":[139],"yield":[140],"weak":[141],"results":[143,192],"easily":[146],"outperformed.":[147],"Finally,":[148],"Lbl2TransformerVec":[152],"approach":[153],"presented,":[155],"which":[156],"outperforms":[157],"previous":[158],"unsupervised":[162],"classification.":[164],"Our":[165],"show":[167],"that":[168],"significantly":[171],"outperform":[172],"most":[176],"cases.":[177],"or":[181],"SBERT":[182],"embeddings":[183],"instead":[184],"simpler":[186],"increases":[189],"even":[193],"further.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":11}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2023-06-28T00:00:00"}