{"id":"https://openalex.org/W4385572673","doi":"https://doi.org/10.18653/v1/2023.findings-acl.244","title":"A Benchmark on Extremely Weakly Supervised Text Classification: Reconcile Seed Matching and Prompting Approaches","display_name":"A Benchmark on Extremely Weakly Supervised Text Classification: Reconcile Seed Matching and Prompting Approaches","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385572673","doi":"https://doi.org/10.18653/v1/2023.findings-acl.244"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.findings-acl.244","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-acl.244","pdf_url":"https://aclanthology.org/2023.findings-acl.244.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":"Findings of the Association for Computational Linguistics: ACL 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.findings-acl.244.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100380108","display_name":"Zihan Wang","orcid":"https://orcid.org/0000-0003-1056-6326"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zihan Wang","raw_affiliation_strings":["University of California, San Diego"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101928623","display_name":"Tianle Wang","orcid":"https://orcid.org/0009-0003-7003-0264"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianle Wang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032931351","display_name":"Dheeraj Mekala","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dheeraj Mekala","raw_affiliation_strings":["University of California, San Diego"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039500313","display_name":"Jingbo Shang","orcid":"https://orcid.org/0000-0002-7249-4404"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingbo Shang","raw_affiliation_strings":["University of California, San Diego"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100380108"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":0.6983,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75345258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9977999925613403,"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":0.9894000291824341,"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":0.7441211938858032},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6498260498046875},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6430509090423584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6162161827087402},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5624403357505798},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.556732177734375},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5252161622047424},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4718365967273712},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.4434274435043335},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.4427783787250519},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4351927638053894},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14029598236083984},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11355626583099365}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7441211938858032},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6498260498046875},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6430509090423584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6162161827087402},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5624403357505798},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.556732177734375},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5252161622047424},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4718365967273712},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.4434274435043335},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.4427783787250519},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4351927638053894},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14029598236083984},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11355626583099365},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.findings-acl.244","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-acl.244","pdf_url":"https://aclanthology.org/2023.findings-acl.244.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":"Findings of the Association for Computational Linguistics: ACL 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.findings-acl.244","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-acl.244","pdf_url":"https://aclanthology.org/2023.findings-acl.244.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":"Findings of the Association for Computational Linguistics: ACL 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385572673.pdf"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1493526108","https://openalex.org/W1978394996","https://openalex.org/W2113459411","https://openalex.org/W2170240176","https://openalex.org/W2593560537","https://openalex.org/W2923014074","https://openalex.org/W2963341956","https://openalex.org/W2965373594","https://openalex.org/W2970200208","https://openalex.org/W3004119480","https://openalex.org/W3034588688","https://openalex.org/W3034640977","https://openalex.org/W3101606352","https://openalex.org/W3103981637","https://openalex.org/W3106109117","https://openalex.org/W3153427360","https://openalex.org/W3156470785","https://openalex.org/W3164972323","https://openalex.org/W3166913490","https://openalex.org/W3172943453","https://openalex.org/W3173777717","https://openalex.org/W3188542058","https://openalex.org/W3192405822","https://openalex.org/W3200496214","https://openalex.org/W3202082017","https://openalex.org/W4205857304","https://openalex.org/W4221167718","https://openalex.org/W4224308101","https://openalex.org/W4226278401","https://openalex.org/W4231510805","https://openalex.org/W4281401697","https://openalex.org/W4292779060","https://openalex.org/W4293997820","https://openalex.org/W4306295130","https://openalex.org/W4307647416","https://openalex.org/W4307937315","https://openalex.org/W4385571291"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2011676020","https://openalex.org/W2770764537"],"abstract_inverted_index":{"Extremely":[0],"Weakly":[1],"Supervised":[2],"Text":[3],"Classification":[4],"(XWS-TC)":[5],"refers":[6],"to":[7,64,76,122,142,171],"text":[8],"classification":[9,24,59,128],"based":[10,41,161],"on":[11,42,81,162],"minimal":[12],"high-level":[13],"human":[14,123],"guidance,":[15],"such":[16],"as":[17,178],"a":[18,157,167,179],"few":[19],"label-indicative":[20],"seed":[21,48,126],"words":[22,49,67],"or":[23],"instructions.":[25],"There":[26],"are":[27,91,106],"two":[28,79],"mainstream":[29],"approaches":[30,80,105],"for":[31],"XWS-TC,":[32],"however,":[33],"never":[34],"being":[35],"rigorously":[36],"compared:":[37],"(1)":[38,100],"training":[39],"classifiers":[40],"pseudo-labels":[43],"generated":[44],"by":[45],"(softly)":[46],"matching":[47],"(Seed)":[50],"and":[51,88,103,108,130,150,156,188,194],"(2)":[52,114],"prompting":[53],"(and":[54,61],"calibrating)":[55],"language":[56,145],"models":[57],"using":[58],"instruction":[60],"raw":[62,163],"texts)":[63],"decode":[65],"label":[66,131],"(Prompt).":[68],"This":[69],"paper":[70],"presents":[71],"the":[72,78,85,143],"first":[73],"XWS-TC":[74,183,196],"benchmark":[75,176],"compare":[77],"fair":[82],"grounds,":[83],"where":[84],"datasets,":[86],"supervisions,":[87],"hyperparameter":[89],"choices":[90],"standardized":[92],"across":[93],"methods.":[94,197],"Our":[95],"benchmarking":[96],"results":[97],"suggest":[98],"that":[99],"Both":[101],"Seed":[102,115,135,149],"Prompt":[104,121,141,151],"competitive":[107],"there":[109],"is":[110,116,136,166],"no":[111],"clear":[112],"winner;":[113],"empirically":[117,137],"more":[118,138],"tolerant":[119],"than":[120,140],"guidance":[124],"(e.g.,":[125],"words,":[127],"instructions,":[129],"words)":[132],"changes;":[133],"(3)":[134],"selective":[139],"pre-trained":[144],"models;":[146],"(4)":[147],"Recent":[148],"methods":[152,184],"have":[153],"close":[154],"connections":[155],"clustering":[158],"post-processing":[159],"step":[160],"in-domain":[164],"texts":[165],"strong":[168],"performance":[169],"booster":[170],"both.":[172],"We":[173],"hope":[174],"this":[175],"serves":[177],"guideline":[180],"in":[181,185,191],"selecting":[182],"different":[186],"scenarios":[187],"stimulate":[189],"interest":[190],"developing":[192],"guidance-":[193],"model-robust":[195]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}