{"id":"https://openalex.org/W2952603081","doi":"https://doi.org/10.18653/v1/p19-1595","title":"BAM! Born-Again Multi-Task Networks for Natural Language Understanding","display_name":"BAM! Born-Again Multi-Task Networks for Natural Language Understanding","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2952603081","doi":"https://doi.org/10.18653/v1/p19-1595","mag":"2952603081"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1595","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1595","pdf_url":"https://www.aclweb.org/anthology/P19-1595.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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1595.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049064405","display_name":"Kevin B. Clark","orcid":"https://orcid.org/0000-0003-0544-2150"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Clark","raw_affiliation_strings":["Computer Science Department, Stanford University  Google Brain","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University  Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078684067","display_name":"Minh-Thang Luong","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minh-Thang Luong","raw_affiliation_strings":["Computer Science Department, Stanford University  Google Brain","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University  Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088072227","display_name":"Urvashi Khandelwal","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Urvashi Khandelwal","raw_affiliation_strings":["Computer Science Department, Stanford University  Google Brain","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University  Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046006076","display_name":"Christopher D. Manning","orcid":"https://orcid.org/0000-0001-6155-649X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher D. Manning","raw_affiliation_strings":["Computer Science Department, Stanford University  Google Brain","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University  Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088551093","display_name":"Quoc V. Le","orcid":"https://orcid.org/0000-0002-1087-2844"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quoc V. Le","raw_affiliation_strings":["Computer Science Department, Stanford University  Google Brain","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University  Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5931","last_page":"5937"},"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":0.9994000196456909,"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":0.7433760166168213},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7080318331718445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5474349856376648},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5334128737449646},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5300310254096985},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.529510498046875},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.520867109298706},{"id":"https://openalex.org/keywords/simulated-annealing","display_name":"Simulated annealing","score":0.4924696385860443},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4581022262573242},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.346184641122818},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08912336826324463}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7433760166168213},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7080318331718445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5474349856376648},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5334128737449646},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5300310254096985},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.529510498046875},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.520867109298706},{"id":"https://openalex.org/C126980161","wikidata":"https://www.wikidata.org/wiki/Q863783","display_name":"Simulated annealing","level":2,"score":0.4924696385860443},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4581022262573242},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.346184641122818},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08912336826324463},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/p19-1595","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1595","pdf_url":"https://www.aclweb.org/anthology/P19-1595.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"},{"id":"pmh:oai:arXiv.org:1907.04829","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.04829","pdf_url":"https://arxiv.org/pdf/1907.04829","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:2952603081","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1907.04829.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1907.04829","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.04829","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1595","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1595","pdf_url":"https://www.aclweb.org/anthology/P19-1595.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":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2952603081.pdf","grobid_xml":"https://content.openalex.org/works/W2952603081.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W131533222","https://openalex.org/W591148856","https://openalex.org/W1821462560","https://openalex.org/W2117130368","https://openalex.org/W2121044470","https://openalex.org/W2130158090","https://openalex.org/W2134797427","https://openalex.org/W2170973209","https://openalex.org/W2251939518","https://openalex.org/W2294370754","https://openalex.org/W2516255829","https://openalex.org/W2556468274","https://openalex.org/W2590925815","https://openalex.org/W2592170186","https://openalex.org/W2624871570","https://openalex.org/W2806120502","https://openalex.org/W2809324505","https://openalex.org/W2898700502","https://openalex.org/W2905933322","https://openalex.org/W2913340405","https://openalex.org/W2914526845","https://openalex.org/W2937297214","https://openalex.org/W2940024477","https://openalex.org/W2951335443","https://openalex.org/W2962739339","https://openalex.org/W2962784628","https://openalex.org/W2962858248","https://openalex.org/W2962897020","https://openalex.org/W2963026768","https://openalex.org/W2963168538","https://openalex.org/W2963199420","https://openalex.org/W2963213121","https://openalex.org/W2963310665","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963748441","https://openalex.org/W2963842982","https://openalex.org/W2963846996","https://openalex.org/W2964222566","https://openalex.org/W2966182616","https://openalex.org/W2974593375","https://openalex.org/W3104033643"],"related_works":["https://openalex.org/W2963453233","https://openalex.org/W2963341956","https://openalex.org/W1821462560","https://openalex.org/W2965373594","https://openalex.org/W2963403868","https://openalex.org/W2963310665","https://openalex.org/W2914526845","https://openalex.org/W2913340405","https://openalex.org/W2624871570","https://openalex.org/W2982976156","https://openalex.org/W2181724605","https://openalex.org/W2590567779","https://openalex.org/W2680401079","https://openalex.org/W1585952056","https://openalex.org/W3118145194","https://openalex.org/W2922338626","https://openalex.org/W3041408132","https://openalex.org/W2949828894","https://openalex.org/W2558150900","https://openalex.org/W2978017171"],"abstract_inverted_index":{"It":[0],"can":[1],"be":[2],"challenging":[3],"to":[4,50],"train":[5],"multi-task":[6,31,55,66,81],"neural":[7],"networks":[8],"that":[9,43],"outperform":[10],"or":[11],"even":[12],"match":[13],"their":[14],"single-task":[15,27,59,79],"counterparts.":[16],"To":[17],"help":[18],"address":[19],"this,":[20],"we":[21],"propose":[22],"using":[23],"knowledge":[24],"distillation":[25,49],"where":[26],"models":[28],"teach":[29],"a":[30,40],"model.":[32],"We":[33,61],"enhance":[34],"this":[35],"training":[36],"with":[37],"teacher":[38],"annealing,":[39],"novel":[41],"method":[42,74],"gradually":[44],"transitions":[45],"the":[46,54,70],"model":[47,56],"from":[48],"supervised":[51],"learning,":[52],"helping":[53],"surpass":[57],"its":[58],"teachers.":[60],"evaluate":[62],"our":[63],"approach":[64],"by":[65],"fine-tuning":[67],"BERT":[68],"on":[69],"GLUE":[71],"benchmark.":[72],"Our":[73],"consistently":[75],"improves":[76],"over":[77],"standard":[78],"and":[80],"training.":[82]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}