{"id":"https://openalex.org/W4385572905","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.73","title":"Zero-Shot Text Classification with Self-Training","display_name":"Zero-Shot Text Classification with Self-Training","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4385572905","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.73"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.emnlp-main.73","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.73","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.emnlp-main.73","pdf_url":"https://aclanthology.org/2022.emnlp-main.73.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.emnlp-main.73.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009715645","display_name":"Ariel Gera","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ariel Gera","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063967207","display_name":"Alon Halfon","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alon Halfon","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032780546","display_name":"Eyal Shnarch","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eyal Shnarch","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068497719","display_name":"Yotam Perlitz","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yotam Perlitz","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107931474","display_name":"Liat Ein\u2010Dor","orcid":"https://orcid.org/0000-0002-9206-4970","observed_orcids":["https://orcid.org/0000-0002-9206-4970"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liat Ein-Dor","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017159143","display_name":"Noam Slonim","orcid":"https://orcid.org/0000-0001-5171-8264","observed_orcids":["https://orcid.org/0000-0001-5171-8264"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Noam Slonim","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":7.3214,"has_fulltext":true,"cited_by_count":57,"citation_normalized_percentile":{"value":0.98108522,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1107","last_page":"1119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6880000233650208,"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":0.6880000233650208,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.302700012922287,"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":0.0015999999595806003,"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/zero-shot-text-classification","display_name":"zero-shot text classification","score":0.9980000257492065},{"id":"https://openalex.org/keywords/self-training","display_name":"self-training","score":0.9980000257492065},{"id":"https://openalex.org/keywords/natural-language-inference","display_name":"natural language inference","score":0.6039999723434448},{"id":"https://openalex.org/keywords/pre-trained-language-models","display_name":"pre-trained language models","score":0.8790000081062317},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.7919999957084656},{"id":"https://openalex.org/keywords/unlabeled-data","display_name":"unlabeled data","score":0.9330000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8416807651519775},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6365847587585449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5872564911842346},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.580486536026001},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5753657221794128},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5552592873573303},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5320148468017578},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5222821235656738},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4419860541820526},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4143930971622467},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36574405431747437},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2022.emnlp-main.73","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.73","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.emnlp-main.73","pdf_url":"https://aclanthology.org/2022.emnlp-main.73.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2210.17541","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.17541","pdf_url":"https://arxiv.org/pdf/2210.17541","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2210.17541","doi":"https://doi.org/10.48550/arxiv.2210.17541","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.17541","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.emnlp-main.73","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.73","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.emnlp-main.73","pdf_url":"https://aclanthology.org/2022.emnlp-main.73.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385572905.pdf","grobid_xml":"https://content.openalex.org/works/W4385572905.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1493526108","https://openalex.org/W1522301498","https://openalex.org/W1985767166","https://openalex.org/W2061873838","https://openalex.org/W2099006396","https://openalex.org/W2106401878","https://openalex.org/W2111316763","https://openalex.org/W2113459411","https://openalex.org/W2130158090","https://openalex.org/W2170240176","https://openalex.org/W2250539671","https://openalex.org/W2293363371","https://openalex.org/W2296714235","https://openalex.org/W2607892599","https://openalex.org/W2896457183","https://openalex.org/W2898700502","https://openalex.org/W2962369866","https://openalex.org/W2970200208","https://openalex.org/W2970971581","https://openalex.org/W2980282514","https://openalex.org/W2981852735","https://openalex.org/W2984353870","https://openalex.org/W2985406498","https://openalex.org/W3022113899","https://openalex.org/W3030163527","https://openalex.org/W3034608141","https://openalex.org/W3089635645","https://openalex.org/W3106109117","https://openalex.org/W3118364895","https://openalex.org/W3124687886","https://openalex.org/W3168921237","https://openalex.org/W3178814223","https://openalex.org/W3194309076","https://openalex.org/W3198002980","https://openalex.org/W3202082017","https://openalex.org/W3205068155","https://openalex.org/W3212106401","https://openalex.org/W4385574298"],"related_works":["https://openalex.org/W4385572284","https://openalex.org/W4385570653","https://openalex.org/W4389524056","https://openalex.org/W2995335514","https://openalex.org/W2777746208","https://openalex.org/W3034608141","https://openalex.org/W6990874711","https://openalex.org/W4407098612","https://openalex.org/W4307937542","https://openalex.org/W4409651000"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2],"large":[3],"pretrained":[4],"language":[5,19],"models":[6,15,41],"have":[7,22],"increased":[8],"attention":[9],"to":[10,30,50,59,101,120],"zero-shot":[11,27,93,118],"text":[12,110],"classification.In":[13],"particular,":[14],"finetuned":[16],"on":[17,95],"natural":[18],"inference":[20],"datasets":[21],"been":[23],"widely":[24],"adopted":[25],"as":[26],"classifiers":[28],"due":[29],"their":[31],"promising":[32],"results":[33],"and":[34,52,78,87],"offthe-shelf":[35],"availability.However,":[36],"the":[37,45,70,80,92,117,121],"fact":[38],"that":[39,90],"such":[40],"are":[42],"unfamiliar":[43],"with":[44,74],"target":[46],"task":[47,122],"can":[48],"lead":[49],"instability":[51],"performance":[53,103],"issues.We":[54],"propose":[55],"a":[56,64,106],"plug-and-play":[57],"method":[58],"bridge":[60],"this":[61],"gap":[62],"using":[63],"simple":[65],"self-training":[66,115],"approach,":[67],"requiring":[68],"only":[69],"class":[71],"names":[72],"along":[73],"an":[75],"unlabeled":[76],"dataset,":[77],"without":[79],"need":[81],"for":[82],"domain":[83],"expertise":[84],"or":[85],"trial":[86],"error.We":[88],"show":[89],"fine-tuning":[91],"classifier":[94],"its":[96],"most":[97],"confident":[98],"predictions":[99],"leads":[100],"significant":[102],"gains":[104],"across":[105],"wide":[107],"range":[108],"of":[109],"classification":[111],"tasks,":[112],"presumably":[113],"since":[114],"adapts":[116],"model":[119],"at":[123],"hand.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":15}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2023-08-05T00:00:00"}