{"id":"https://openalex.org/W4392903808","doi":"https://doi.org/10.1109/icassp48485.2024.10446315","title":"Taming Prompt-Based Data Augmentation for Long-Tailed Extreme Multi-Label Text Classification","display_name":"Taming Prompt-Based Data Augmentation for Long-Tailed Extreme Multi-Label Text Classification","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903808","doi":"https://doi.org/10.1109/icassp48485.2024.10446315"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5064324887","display_name":"Pengyu Xu","orcid":"https://orcid.org/0000-0002-3176-6944"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pengyu Xu","raw_affiliation_strings":["Beijing Jiaotong University,Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China","Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063533156","display_name":"Mingyang Song","orcid":"https://orcid.org/0000-0001-9492-261X"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyang Song","raw_affiliation_strings":["Beijing Jiaotong University,Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China","Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389145","display_name":"Ziyi Li","orcid":"https://orcid.org/0009-0007-0881-1034"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyi Li","raw_affiliation_strings":["Beijing Jiaotong University,Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China","Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113021204","display_name":"Sijin Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sijin Lu","raw_affiliation_strings":["Beijing Jiaotong University,Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China","Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069749738","display_name":"Liping Jing","orcid":"https://orcid.org/0000-0001-7578-3407"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liping Jing","raw_affiliation_strings":["Beijing Jiaotong University,Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China","Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027501725","display_name":"Jian Yu","orcid":"https://orcid.org/0000-0002-9488-5182"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yu","raw_affiliation_strings":["Beijing Jiaotong University,Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China","Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5064324887"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":0.669,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72300146,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"9981","last_page":"9985"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9907000064849854,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9790999889373779,"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":0.7779924869537354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5501636862754822},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4513895809650421},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4512062966823578},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4283856749534607},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42752882838249207},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4015379250049591},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3937433063983917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7779924869537354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5501636862754822},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4513895809650421},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4512062966823578},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4283856749534607},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42752882838249207},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4015379250049591},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3937433063983917},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1614471940","display_name":null,"funder_award_id":"2020AAA0","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2326706895","display_name":null,"funder_award_id":"2020AAA0106800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2507855583","display_name":null,"funder_award_id":"202004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4118857521","display_name":null,"funder_award_id":"62176020","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4682237683","display_name":null,"funder_award_id":"OEIP-O-202004","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"id":"https://openalex.org/G5462800882","display_name":null,"funder_award_id":"2019JBZ110","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7921077220","display_name":null,"funder_award_id":"176020","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"id":"https://openalex.org/G8377820436","display_name":null,"funder_award_id":"2019JBZ110","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8439589750","display_name":null,"funder_award_id":"2019JBZ110","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2362855512","https://openalex.org/W2520348554","https://openalex.org/W2788125153","https://openalex.org/W2987098737","https://openalex.org/W2998184481","https://openalex.org/W3037422790","https://openalex.org/W3080802002","https://openalex.org/W3095707208","https://openalex.org/W3172352177","https://openalex.org/W3177232285","https://openalex.org/W3194325860","https://openalex.org/W4205991051","https://openalex.org/W4221159394","https://openalex.org/W4224921414","https://openalex.org/W4285183190","https://openalex.org/W4285206067","https://openalex.org/W4288089799","https://openalex.org/W4362581824","https://openalex.org/W4364302133","https://openalex.org/W4382202983","https://openalex.org/W4386566607","https://openalex.org/W6631190155","https://openalex.org/W6767075311","https://openalex.org/W6769627184","https://openalex.org/W6780300825"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"In":[0,42,111],"extreme":[1],"multi-label":[2],"text":[3,98],"classification":[4],"(XMC),":[5],"labels":[6,14],"usually":[7],"follow":[8],"a":[9,17,32,47,62,119],"long-tailed":[10,136],"distribution,":[11],"where":[12],"most":[13],"only":[15],"contain":[16],"small":[18],"number":[19],"of":[20,26,69,97,102,108,129],"documents":[21],"and":[22,99],"limit":[23],"the":[24,66,70,91,95,100,106,109,125,135,146,150],"performance":[25],"XMC.":[27,58],"Data":[28],"augmentation":[29],"(DA)":[30],"is":[31,54],"simple":[33],"but":[34],"effective":[35],"strategy":[36],"to":[37,79,113],"solve":[38],"such":[39],"low-resource":[40],"problems.":[41],"this":[43],"paper,":[44],"we":[45,60,117],"propose":[46,118],"prompt-based":[48],"DA":[49,121],"method":[50,122],"called":[51],"XDA,":[52],"which":[53,104],"specifically":[55],"designed":[56],"for":[57,73],"First,":[59],"employ":[61],"soft":[63],"prompt":[64],"during":[65,131],"fine-tuning":[67],"process":[68],"T5":[71,78],"model":[72],"label-conditional":[74],"DA,":[75,116],"thereby":[76],"enabling":[77],"augment":[80],"samples":[81,93],"while":[82],"preserving":[83],"label-compatibility.":[84],"Subsequently,":[85],"XDA":[86,148],"performs":[87],"sample":[88],"filtering":[89],"on":[90,140],"augmented":[92,126],"through":[94],"diversity":[96],"consistency":[101],"labels,":[103],"enhances":[105],"quality":[107],"DA.":[110],"contrast":[112],"traditional":[114],"sample-level":[115],"pair-level":[120],"by":[123],"masking":[124],"sample-label":[127],"pairs":[128],"head-labels":[130],"training,":[132],"effectively":[133],"mitigating":[134],"problem.":[137],"Comprehensive":[138],"experiments":[139],"benchmark":[141],"datasets":[142],"have":[143],"shown":[144],"that":[145],"proposed":[147],"outperforms":[149],"state-of-the-art":[151],"counterparts.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}