{"id":"https://openalex.org/W3114034564","doi":"https://doi.org/10.1145/3437963.3441814","title":"Semi-Supervised Text Classification via Self-Pretraining","display_name":"Semi-Supervised Text Classification via Self-Pretraining","publication_year":2021,"publication_date":"2021-03-06","ids":{"openalex":"https://openalex.org/W3114034564","doi":"https://doi.org/10.1145/3437963.3441814","mag":"3114034564"},"language":"en","primary_location":{"id":"doi:10.1145/3437963.3441814","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437963.3441814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Web Search and Data Mining","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/A5082947318","display_name":"Payam Karisani","orcid":"https://orcid.org/0000-0002-7756-3608"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Payam Karisani","raw_affiliation_strings":["Emory University, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009411767","display_name":"Negin Karisani","orcid":"https://orcid.org/0000-0002-9858-5654"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Negin Karisani","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082947318"],"corresponding_institution_ids":["https://openalex.org/I150468666"],"apc_list":null,"apc_paid":null,"fwci":2.5835,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.91067188,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"40","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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":0.9988999962806702,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9988999962806702,"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":0.9973000288009644,"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":0.787941575050354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6846228241920471},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6106734275817871},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5500260591506958},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4132336378097534},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40104439854621887}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.787941575050354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6846228241920471},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6106734275817871},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5500260591506958},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4132336378097534},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40104439854621887},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3437963.3441814","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437963.3441814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1479807131","https://openalex.org/W1560659665","https://openalex.org/W2052110545","https://openalex.org/W2111316763","https://openalex.org/W2560647685","https://openalex.org/W2895094948","https://openalex.org/W2911489562","https://openalex.org/W2943865428","https://openalex.org/W2945540071","https://openalex.org/W2950799135","https://openalex.org/W2953070460","https://openalex.org/W2962739339","https://openalex.org/W2962804657","https://openalex.org/W2963261224","https://openalex.org/W2963326042","https://openalex.org/W2963930099","https://openalex.org/W2976192278","https://openalex.org/W2978426779","https://openalex.org/W2980282514","https://openalex.org/W3010559454","https://openalex.org/W3012633454","https://openalex.org/W3037311587","https://openalex.org/W3146668661","https://openalex.org/W6745136726"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3209574120","https://openalex.org/W3107602296","https://openalex.org/W2033914206","https://openalex.org/W4312192474","https://openalex.org/W4210805261"],"abstract_inverted_index":{"We":[0,145],"present":[1],"a":[2,58,129,141],"neural":[3],"semi-supervised":[4,166],"learning":[5,136],"model":[6,10,149],"termed":[7],"Self-Pretraining.":[8],"Our":[9,157,171],"is":[11,24,45,69,173],"inspired":[12],"by":[13,80],"the":[14,40,73,81,90,94,101,106,113,126,163],"classic":[15],"self-training":[16],"algorithm.":[17],"However,":[18],"as":[19],"opposed":[20],"to":[21,71,76,89,110],"self-training,":[22],"Self-Pretraining":[23,44,117,161],"threshold-free,":[25],"it":[26],"can":[27,37],"potentially":[28],"update":[29],"its":[30],"belief":[31],"about":[32],"previously":[33],"labeled":[34,84],"documents,":[35],"and":[36,47,64,93,108,139],"cope":[38,111],"with":[39,112],"semantic":[41,114],"drift":[42,115],"problem.":[43],"iterative":[46,120],"consists":[48],"of":[49,61,83,103],"two":[50],"classifiers.":[51],"In":[52],"each":[53],"iteration,":[54],"one":[55],"classifier":[56],"draws":[57],"random":[59],"set":[60,68,82],"unlabeled":[62],"documents":[63],"labels":[65],"them.":[66],"This":[67],"used":[70],"initialize":[72],"second":[74],"classifier,":[75],"be":[77],"further":[78],"trained":[79],"documents.":[85],"The":[86],"algorithm":[87],"proceeds":[88],"next":[91],"iteration":[92],"classifiers'":[95],"roles":[96],"are":[97],"reversed.":[98],"To":[99],"improve":[100],"flow":[102],"information":[104],"across":[105,125,168],"iterations":[107],"also":[109],"problem,":[116],"employs":[118,140],"an":[119,134],"distillation":[121],"process,":[122],"transfers":[123],"hypotheses":[124],"iterations,":[127],"utilizes":[128],"two-stage":[130],"training":[131],"model,":[132],"uses":[133],"efficient":[135],"rate":[137],"schedule,":[138],"pseudo-label":[142],"transformation":[143],"heuristic.":[144],"have":[146],"evaluated":[147],"our":[148],"in":[150],"three":[151],"publicly":[152],"available":[153,174],"social":[154],"media":[155],"datasets.":[156],"experiments":[158],"show":[159],"that":[160],"outperforms":[162],"existing":[164],"state-of-the-art":[165],"classifiers":[167],"multiple":[169],"settings.":[170],"code":[172],"at":[175],"https://github.com/p-karisani/self-pretraining":[176],".":[177]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}