{"id":"https://openalex.org/W4396214772","doi":"https://doi.org/10.1109/taslp.2024.3394774","title":"Learning to Improve Out-of-Distribution Generalization via Self-Adaptive Language Masking","display_name":"Learning to Improve Out-of-Distribution Generalization via Self-Adaptive Language Masking","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4396214772","doi":"https://doi.org/10.1109/taslp.2024.3394774"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3394774","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/taslp.2024.3394774","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5040208886","display_name":"Shuoran Jiang","orcid":"https://orcid.org/0000-0001-5888-0328"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuoran Jiang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China","Harbin Institute of Technology (Shenzhen), China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004433495","display_name":"Youcheng Pan","orcid":"https://orcid.org/0000-0002-8270-5455"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youcheng Pan","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101895423","display_name":"Qingcai Chen","orcid":"https://orcid.org/0000-0001-8473-7293"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingcai Chen","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China","Harbin Institute of Technology (Shenzhen), China","Peng Cheng Laboratory, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Peng Cheng Laboratory, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101632572","display_name":"Yang Xiang","orcid":"https://orcid.org/0000-0003-1395-6805"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Xiang","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050877497","display_name":"Xiangping Wu","orcid":"https://orcid.org/0000-0002-5267-2250"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangping Wu","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China","Harbin Institute of Technology (Shenzhen), China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5040208886"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.3491,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62422807,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"32","issue":null,"first_page":"2739","last_page":"2750"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7309100031852722},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6067774295806885},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.5886679291725159},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5856376886367798},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5836988687515259},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5196148753166199},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.4894603490829468},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4336106777191162},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3365514278411865},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3242088556289673},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.21480801701545715},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.153929203748703}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7309100031852722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6067774295806885},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.5886679291725159},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5856376886367798},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5836988687515259},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5196148753166199},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.4894603490829468},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4336106777191162},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3365514278411865},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3242088556289673},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.21480801701545715},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.153929203748703},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3394774","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/taslp.2024.3394774","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2753377255","display_name":null,"funder_award_id":"62006062","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4619845879","display_name":null,"funder_award_id":"2023A1515110561","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G6233398042","display_name":null,"funder_award_id":"62106115","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6312846351","display_name":null,"funder_award_id":"62176076","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6430788580","display_name":null,"funder_award_id":"62276075","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8627319070","display_name":null,"funder_award_id":"2023M741843","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G888125545","display_name":null,"funder_award_id":"XMHT20190108009","funder_id":"https://openalex.org/F4320327511","funder_display_name":"Development and Reform Commission of Shenzhen Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320327511","display_name":"Development and Reform Commission of Shenzhen Municipality","ror":"https://ror.org/03jmg4515"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W2413794162","https://openalex.org/W2608787653","https://openalex.org/W2618530766","https://openalex.org/W2896457183","https://openalex.org/W2951286828","https://openalex.org/W2951568144","https://openalex.org/W2953903036","https://openalex.org/W2955315229","https://openalex.org/W2963748441","https://openalex.org/W2963846996","https://openalex.org/W2963961878","https://openalex.org/W2970019270","https://openalex.org/W2970379526","https://openalex.org/W2984256198","https://openalex.org/W3011574394","https://openalex.org/W3024308166","https://openalex.org/W3031914912","https://openalex.org/W3034775979","https://openalex.org/W3034781633","https://openalex.org/W3034831508","https://openalex.org/W3035377849","https://openalex.org/W3088409176","https://openalex.org/W3092747189","https://openalex.org/W3095992020","https://openalex.org/W3099023595","https://openalex.org/W3100895823","https://openalex.org/W3101004475","https://openalex.org/W3108655343","https://openalex.org/W3115295967","https://openalex.org/W3152911627","https://openalex.org/W3169001897","https://openalex.org/W3173783447","https://openalex.org/W3173787059","https://openalex.org/W3187071356","https://openalex.org/W3196850540","https://openalex.org/W3199589346","https://openalex.org/W3200768867","https://openalex.org/W3202712981","https://openalex.org/W3204601267","https://openalex.org/W4287162887","https://openalex.org/W4306955484","https://openalex.org/W4385245566","https://openalex.org/W4385756462","https://openalex.org/W4399929809","https://openalex.org/W6631190155","https://openalex.org/W6679819393","https://openalex.org/W6753579488","https://openalex.org/W6762521896","https://openalex.org/W6765039553","https://openalex.org/W6776148200","https://openalex.org/W6776699476","https://openalex.org/W6779469252","https://openalex.org/W6784404284","https://openalex.org/W6787655056","https://openalex.org/W6797155008","https://openalex.org/W6797378770","https://openalex.org/W6797398724","https://openalex.org/W6800440403","https://openalex.org/W6801491556","https://openalex.org/W6804272589","https://openalex.org/W6839666850","https://openalex.org/W6842940110"],"related_works":["https://openalex.org/W4220972140","https://openalex.org/W3161120485","https://openalex.org/W1773599773","https://openalex.org/W2268150819","https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W3098382480","https://openalex.org/W4287598411"],"abstract_inverted_index":{"Although":[0],"the":[1,15,26,53,62,76,81,93,108,111,115,128,133],"pre-trained":[2,29,54,137],"Transformers":[3],"learned":[4],"general":[5],"linguistic":[6],"knowledge":[7],"from":[8],"large-scale":[9],"corpus,":[10],"they":[11],"still":[12],"over-fit":[13],"on":[14,20,64,114],"lexical":[16,58,118],"biases":[17,59,119],"when":[18,32],"fine-tuning":[19],"specific":[21],"datasets.":[22],"This":[23],"problem":[24],"limits":[25],"generalizability":[27],"of":[28,110,117,136],"models,":[30],"particularly":[31],"learning":[33],"over":[34],"out-of-distribution":[35],"(OOD)":[36],"data.":[37],"To":[38],"address":[39],"this":[40,42],"issue,":[41],"paper":[43],"proposes":[44],"a":[45,71,87],"self-adaptive":[46],"language":[47,101],"masking":[48,78],"(AdaLMask)":[49],"paradigm":[50,130],"to":[51,74,91,106],"fine-tune":[52],"Transformers.":[55,138],"AdaLMask":[56,69,129],"obviates":[57],"by":[60],"eliminating":[61],"dependence":[63],"semantically":[65,97],"inessential":[66],"words.":[67],"Specifically,":[68],"learns":[70],"Gumbel-Softmax":[72],"distribution":[73,82],"determine":[75],"desired":[77],"positions,":[79],"and":[80,120],"parameters":[83],"are":[84,96,104],"optimized":[85],"via":[86],"representation-invariant":[88],"(RInv)":[89],"objective":[90],"ensure":[92],"masked":[94],"positions":[95],"lossless.":[98],"Four":[99],"natural":[100],"processing":[102],"tasks":[103],"chosen":[105],"evaluate":[107],"effectiveness":[109],"proposed":[112],"method":[113],"robustness":[116],"OOD":[121,134],"generalization.":[122],"All":[123],"empirical":[124],"results":[125],"demonstrate":[126],"that":[127],"substantially":[131],"improves":[132],"generalization":[135]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}