{"id":"https://openalex.org/W2963854351","doi":"https://doi.org/10.18653/v1/p19-1441","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","display_name":"Multi-Task Deep Neural Networks for Natural Language Understanding","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2963854351","doi":"https://doi.org/10.18653/v1/p19-1441","mag":"2963854351"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1441","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1441","pdf_url":"https://www.aclweb.org/anthology/P19-1441.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":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1441.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100374810","display_name":"Xiaodong Liu","orcid":"https://orcid.org/0009-0004-6648-2302"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Xiaodong Liu","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019259019","display_name":"Pengcheng He","orcid":"https://orcid.org/0000-0002-7860-503X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pengcheng He","raw_affiliation_strings":["Microsoft Dynamics 365 AI"],"affiliations":[{"raw_affiliation_string":"Microsoft Dynamics 365 AI","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051745436","display_name":"Weizhu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weizhu Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5114910293","display_name":"Jianfeng Gao","orcid":"https://orcid.org/0000-0002-5702-6143"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Jianfeng Gao","raw_affiliation_strings":["Microsoft Dynamics 365 AI","Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Dynamics 365 AI","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100374810"],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":105.6211,"has_fulltext":true,"cited_by_count":1043,"citation_normalized_percentile":{"value":0.99963706,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4487","last_page":"4496"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/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":0.9973999857902527,"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":0.811676025390625},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.7389097809791565},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.661305844783783},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6017350554466248},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5892266035079956},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.5881803631782532},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5494886040687561},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5417402982711792},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.534062922000885},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5109745264053345},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46602603793144226},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.42734095454216003},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4234755039215088},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41908901929855347},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41811811923980713},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.416551411151886},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40958651900291443},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3868917226791382}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.811676025390625},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.7389097809791565},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.661305844783783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6017350554466248},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5892266035079956},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.5881803631782532},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5494886040687561},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5417402982711792},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.534062922000885},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5109745264053345},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46602603793144226},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.42734095454216003},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4234755039215088},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41908901929855347},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41811811923980713},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.416551411151886},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40958651900291443},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3868917226791382},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1441","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1441","pdf_url":"https://www.aclweb.org/anthology/P19-1441.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":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1441","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1441","pdf_url":"https://www.aclweb.org/anthology/P19-1441.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":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8100000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963854351.pdf","grobid_xml":"https://content.openalex.org/works/W2963854351.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1840435438","https://openalex.org/W2136189984","https://openalex.org/W2143331230","https://openalex.org/W2158899491","https://openalex.org/W2295072214","https://openalex.org/W2742079690","https://openalex.org/W2788496822","https://openalex.org/W2798459010","https://openalex.org/W2798665661","https://openalex.org/W2810840719","https://openalex.org/W2891439916","https://openalex.org/W2896457183","https://openalex.org/W2898700502","https://openalex.org/W2913340405","https://openalex.org/W2923014074","https://openalex.org/W2937297214","https://openalex.org/W2945260553","https://openalex.org/W2952230511","https://openalex.org/W2962739339","https://openalex.org/W2963310665","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963748441","https://openalex.org/W2963769536","https://openalex.org/W2963842982","https://openalex.org/W2964082993","https://openalex.org/W2964121744","https://openalex.org/W2964285114","https://openalex.org/W2966182616","https://openalex.org/W2971274815","https://openalex.org/W2972987451","https://openalex.org/W4292356436","https://openalex.org/W4306716473","https://openalex.org/W4322614701","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3035557009","https://openalex.org/W2955172689","https://openalex.org/W2341113105","https://openalex.org/W3204418343","https://openalex.org/W3132602785","https://openalex.org/W3046182208","https://openalex.org/W2186589590","https://openalex.org/W4297818280","https://openalex.org/W2343346879","https://openalex.org/W772479628"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,34],"Multi-Task":[6],"Deep":[7],"Neural":[8],"Network":[9],"(MT-DNN)":[10],"for":[11],"learning":[12],"representations":[13,42,102],"across":[14],"multiple":[15],"natural":[16],"language":[17],"understanding":[18],"(NLU)":[19],"tasks.":[20],"MT-DNN":[21,51,61,105],"not":[22],"only":[23],"leverages":[24],"large":[25],"amounts":[26],"of":[27,76],"cross-task":[28],"data,":[29],"but":[30],"also":[31,92],"benefits":[32],"from":[33],"regularization":[35],"effect":[36],"that":[37,100],"leads":[38],"to":[39,43,46,84],"more":[40],"general":[41],"help":[44],"adapt":[45],"new":[47,63],"tasks":[48],"and":[49,73,97,121],"domains.":[50],"extends":[52],"the":[53,81,95,101,115],"model":[54],"proposed":[55],"in":[56],"Liu":[57],"et":[58],"al.":[59],"(":[60],"obtains":[62],"state-of-the-art":[64],"results":[65],"on":[66],"ten":[67],"NLU":[68],"tasks,":[69,79],"including":[70],"SNLI,":[71],"SciTail,":[72],"eight":[74],"out":[75],"nine":[77],"GLUE":[78,82],"pushing":[80],"benchmark":[83],"82.7%":[85],"(2.2%":[86],"absolute":[87],"improvement)":[88],"1":[89],".":[90],"We":[91],"demonstrate":[93],"using":[94],"SNLI":[96],"Sc-iTail":[98],"datasets":[99],"learned":[103],"by":[104],"allow":[106],"domain":[107],"adaptation":[108],"with":[109],"substantially":[110],"fewer":[111],"in-domain":[112],"labels":[113],"than":[114],"pre-trained":[116,122],"BERT":[117],"representations.":[118],"The":[119],"code":[120],"models":[123],"are":[124],"publicly":[125],"available":[126],"at":[127],"https://github.com/namisan/mt-dnn.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":62},{"year":2024,"cited_by_count":86},{"year":2023,"cited_by_count":158},{"year":2022,"cited_by_count":154},{"year":2021,"cited_by_count":254},{"year":2020,"cited_by_count":220},{"year":2019,"cited_by_count":101},{"year":2018,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}