{"id":"https://openalex.org/W4287120901","doi":"https://doi.org/10.1162/tacl_a_00492","title":"Generate, Annotate, and Learn: NLP with Synthetic Text","display_name":"Generate, Annotate, and Learn: NLP with Synthetic Text","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4287120901","doi":"https://doi.org/10.1162/tacl_a_00492"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00492","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00492","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00492/2038511/tacl_a_00492.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00492/2038511/tacl_a_00492.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060320196","display_name":"Xuanli He","orcid":null},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Xuanli He","raw_affiliation_strings":["Monash University, Australia. xuanli.he1@monash.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University, Australia. xuanli.he1@monash.edu","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055650983","display_name":"Islam Nassar","orcid":null},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Islam Nassar","raw_affiliation_strings":["Monash University, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065231880","display_name":"Jamie Kiros","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148186","display_name":"Google (Canada)","ror":"https://ror.org/04d06q394","country_code":"CA","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969","https://openalex.org/I4210148186"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jamie Kiros","raw_affiliation_strings":["Google Research, Brain Team, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Brain Team, Canada","institution_ids":["https://openalex.org/I4210148186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081525024","display_name":"Gholamreza Haffari","orcid":"https://orcid.org/0000-0001-7326-8380"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Gholamreza Haffari","raw_affiliation_strings":["Monash University, Australia. gholamreza.haffari@monash.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University, Australia. gholamreza.haffari@monash.edu","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103947107","display_name":"Mohammad Norouzi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148186","display_name":"Google (Canada)","ror":"https://ror.org/04d06q394","country_code":"CA","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969","https://openalex.org/I4210148186"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Mohammad Norouzi","raw_affiliation_strings":["Google Research, Brain Team, Canada. mnorouzi@google.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Brain Team, Canada. mnorouzi@google.com","institution_ids":["https://openalex.org/I4210148186"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060320196","https://openalex.org/A5081525024","https://openalex.org/A5103947107"],"corresponding_institution_ids":["https://openalex.org/I4210148186","https://openalex.org/I56590836"],"apc_list":null,"apc_paid":null,"fwci":4.33,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":{"value":0.94966508,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"10","issue":null,"first_page":"826","last_page":"842"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9900000095367432,"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":0.8715073466300964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7153427600860596},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5813819766044617},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5442332625389099},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5363373160362244},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47574540972709656},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.46765631437301636},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45325005054473877},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.44184964895248413},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43022286891937256}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8715073466300964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7153427600860596},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5813819766044617},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5442332625389099},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5363373160362244},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47574540972709656},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.46765631437301636},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45325005054473877},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.44184964895248413},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43022286891937256},{"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1162/tacl_a_00492","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00492","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00492/2038511/tacl_a_00492.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:monash.edu:openaire/9f321265-7e68-4688-aefe-63ad91c8cf5c","is_oa":true,"landing_page_url":"https://research.monash.edu/en/publications/9f321265-7e68-4688-aefe-63ad91c8cf5c","pdf_url":null,"source":{"id":"https://openalex.org/S4306402625","display_name":"Monash University Research Portal (Monash University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I56590836","host_organization_name":"Monash University","host_organization_lineage":["https://openalex.org/I56590836"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"He, X, Nassar, I, Kiros, J, Haffari, G & Norouzi, M 2022, 'Generate, annotate, and learn : NLP with synthetic text', Transactions of the Association for Computational Linguistics, vol. 10, pp. 826-842. https://doi.org/10.1162/tacl_a_00492","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:64199a6a11594068a7161ea6f5e73ca3","is_oa":false,"landing_page_url":"https://doaj.org/article/64199a6a11594068a7161ea6f5e73ca3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 10 (2022)","raw_type":"article"},{"id":"pmh:oai:monash.edu:publications/9f321265-7e68-4688-aefe-63ad91c8cf5c","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85138749499&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306402625","display_name":"Monash University Research Portal (Monash University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I56590836","host_organization_name":"Monash University","host_organization_lineage":["https://openalex.org/I56590836"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"He , X , Nassar , I , Kiros , J , Haffari , G & Norouzi , M 2022 , ' Generate, annotate, and learn : NLP with synthetic text ' , Transactions of the Association for Computational Linguistics , vol. 10 , pp. 826-842 . https://doi.org/10.1162/tacl_a_00492","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00492","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00492","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00492/2038511/tacl_a_00492.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8600000143051147}],"awards":[{"id":"https://openalex.org/G3717735613","display_name":null,"funder_award_id":"FA8750-19-2-0501","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":107,"referenced_works":["https://openalex.org/W1490960179","https://openalex.org/W1583837637","https://openalex.org/W1821462560","https://openalex.org/W1988529147","https://openalex.org/W2091146638","https://openalex.org/W2101210369","https://openalex.org/W2105580583","https://openalex.org/W2111316763","https://openalex.org/W2151239833","https://openalex.org/W2152005244","https://openalex.org/W2155195660","https://openalex.org/W2251658415","https://openalex.org/W2251957808","https://openalex.org/W2294370754","https://openalex.org/W2765407302","https://openalex.org/W2798858969","https://openalex.org/W2799051177","https://openalex.org/W2803023299","https://openalex.org/W2891534142","https://openalex.org/W2903396356","https://openalex.org/W2905266130","https://openalex.org/W2922917409","https://openalex.org/W2923014074","https://openalex.org/W2933138175","https://openalex.org/W2936597270","https://openalex.org/W2938830017","https://openalex.org/W2943552823","https://openalex.org/W2945027741","https://openalex.org/W2949849869","https://openalex.org/W2962965405","https://openalex.org/W2963121782","https://openalex.org/W2963216553","https://openalex.org/W2963545917","https://openalex.org/W2963736842","https://openalex.org/W2963929190","https://openalex.org/W2964289193","https://openalex.org/W2965373594","https://openalex.org/W2970295111","https://openalex.org/W2970454332","https://openalex.org/W2970680991","https://openalex.org/W2971296908","https://openalex.org/W2978017171","https://openalex.org/W2979826702","https://openalex.org/W2987861506","https://openalex.org/W2998617917","https://openalex.org/W3001197829","https://openalex.org/W3005444338","https://openalex.org/W3014521650","https://openalex.org/W3015385717","https://openalex.org/W3035160371","https://openalex.org/W3036166850","https://openalex.org/W3089659770","https://openalex.org/W3090196146","https://openalex.org/W3100859887","https://openalex.org/W3101248447","https://openalex.org/W3103291112","https://openalex.org/W3105966348","https://openalex.org/W3115582371","https://openalex.org/W3122890974","https://openalex.org/W3168921237","https://openalex.org/W3170014162","https://openalex.org/W3174731106","https://openalex.org/W3174828871","https://openalex.org/W3198270094","https://openalex.org/W3201363102","https://openalex.org/W4205807230","https://openalex.org/W4286901099","https://openalex.org/W4287811262","https://openalex.org/W4287824654","https://openalex.org/W4287829148","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4295253143","https://openalex.org/W6637112725","https://openalex.org/W6638523607","https://openalex.org/W6677294168","https://openalex.org/W6682208247","https://openalex.org/W6682891771","https://openalex.org/W6745136726","https://openalex.org/W6751751081","https://openalex.org/W6756633790","https://openalex.org/W6760456230","https://openalex.org/W6761910064","https://openalex.org/W6762392948","https://openalex.org/W6762707182","https://openalex.org/W6762987983","https://openalex.org/W6766673545","https://openalex.org/W6768851824","https://openalex.org/W6769627184","https://openalex.org/W6771917389","https://openalex.org/W6773005947","https://openalex.org/W6773992155","https://openalex.org/W6774076947","https://openalex.org/W6774085601","https://openalex.org/W6774569510","https://openalex.org/W6775445713","https://openalex.org/W6777388090","https://openalex.org/W6778883912","https://openalex.org/W6779068807","https://openalex.org/W6779320875","https://openalex.org/W6779678126","https://openalex.org/W6779977557","https://openalex.org/W6783973398","https://openalex.org/W6784232266","https://openalex.org/W6790209031","https://openalex.org/W6802302390","https://openalex.org/W6893640197"],"related_works":["https://openalex.org/W3049463507","https://openalex.org/W2936497627","https://openalex.org/W4288365749","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W4287598411","https://openalex.org/W3098382480","https://openalex.org/W3198458223","https://openalex.org/W4288267738","https://openalex.org/W3126642501"],"abstract_inverted_index":{"Abstract":[0],"This":[1],"paper":[2],"studies":[3],"the":[4,55,68,101,129,154],"use":[5,67,86,130],"of":[6,12,32,57,103,120,131,140],"language":[7],"models":[8,99],"as":[9],"a":[10,20],"source":[11],"synthetic":[13,33,74,136],"unlabeled":[14,141],"text":[15,34,75,138],"for":[16,80,92,150],"NLP.":[17],"We":[18,66,95,116],"formulate":[19],"general":[21],"framework":[22],"called":[23],"\u201cgenerate,":[24],"annotate,":[25],"and":[26,39,83,85,105,122,125],"learn":[27],"(GAL)\u201d":[28],"to":[29,72,88,134],"take":[30],"advantage":[31],"within":[35],"knowledge":[36,81,147],"distillation,":[37],"self-training,":[38,84],"few-shot":[40,93],"learning":[41],"applications.":[42,115],"To":[43],"generate":[44,135],"high-quality":[45],"task-specific":[46],"text,":[47],"we":[48],"either":[49],"fine-tune":[50],"LMs":[51,62,87,133],"on":[52,100,153],"inputs":[53],"from":[54],"task":[56],"interest,":[58],"or":[59],"prompt":[60],"large":[61],"with":[63,76],"few":[64],"examples.":[65],"best":[69],"available":[70],"classifier":[71],"annotate":[73],"soft":[77],"pseudo":[78],"labels":[79,91],"distillation":[82,148],"obtain":[89],"hard":[90],"learning.":[94],"train":[96],"new":[97,145],"supervised":[98],"combination":[102],"labeled":[104,137],"pseudo-labeled":[106],"data,":[107],"which":[108],"results":[109,149],"in":[110],"significant":[111],"gains":[112],"across":[113],"several":[114],"investigate":[117],"key":[118],"components":[119],"GAL":[121,143],"present":[123],"theoretical":[124],"empirical":[126],"arguments":[127],"against":[128],"class-conditional":[132],"instead":[139],"text.":[142],"achieves":[144],"state-of-the-art":[146],"6-layer":[151],"transformers":[152],"GLUE":[155],"leaderboard.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":8}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}