{"id":"https://openalex.org/W2972427545","doi":"https://doi.org/10.18653/v1/k19-1084","title":"Global Autoregressive Models for Data-Efficient Sequence Learning","display_name":"Global Autoregressive Models for Data-Efficient Sequence Learning","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2972427545","doi":"https://doi.org/10.18653/v1/k19-1084","mag":"2972427545"},"language":"en","primary_location":{"id":"doi:10.18653/v1/k19-1084","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k19-1084","pdf_url":"https://www.aclweb.org/anthology/K19-1084.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 23rd Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/K19-1084.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046834086","display_name":"Tetiana Parshakova","orcid":"https://orcid.org/0000-0002-7126-4666"},"institutions":[{"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":true,"raw_author_name":"Tetiana Parshakova","raw_affiliation_strings":["Stanford University","Stanford University ()"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111471163","display_name":"Jean\u2010Marc Andreoli","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jean-Marc Andreoli","raw_affiliation_strings":["Naver Labs Europe","NAVER CORPORATION"],"affiliations":[{"raw_affiliation_string":"Naver Labs Europe","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER CORPORATION","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059468860","display_name":"Marc Dymetman","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Marc Dymetman","raw_affiliation_strings":["Naver Labs Europe","NAVER CORPORATION"],"affiliations":[{"raw_affiliation_string":"Naver Labs Europe","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER CORPORATION","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046834086"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10402301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"900","last_page":"909"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994000196456909,"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":0.9975000023841858,"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/autoregressive-model","display_name":"Autoregressive model","score":0.9219081401824951},{"id":"https://openalex.org/keywords/nonlinear-autoregressive-exogenous-model","display_name":"Nonlinear autoregressive exogenous model","score":0.6096893548965454},{"id":"https://openalex.org/keywords/star-model","display_name":"STAR model","score":0.5941718816757202},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5582025647163391},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.5163108706474304},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.504747748374939},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48876047134399414},{"id":"https://openalex.org/keywords/setar","display_name":"SETAR","score":0.475301593542099},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.42759302258491516},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4201146364212036},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4156635105609894},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3977661728858948},{"id":"https://openalex.org/keywords/autoregressive-integrated-moving-average","display_name":"Autoregressive integrated moving average","score":0.3260136544704437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2944079041481018},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.27310729026794434},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.25203168392181396},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.20054590702056885},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1761571168899536}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.9219081401824951},{"id":"https://openalex.org/C42536954","wikidata":"https://www.wikidata.org/wiki/Q7049462","display_name":"Nonlinear autoregressive exogenous model","level":3,"score":0.6096893548965454},{"id":"https://openalex.org/C194657046","wikidata":"https://www.wikidata.org/wiki/Q7394685","display_name":"STAR model","level":4,"score":0.5941718816757202},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5582025647163391},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.5163108706474304},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.504747748374939},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48876047134399414},{"id":"https://openalex.org/C30795276","wikidata":"https://www.wikidata.org/wiki/Q7389877","display_name":"SETAR","level":5,"score":0.475301593542099},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.42759302258491516},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4201146364212036},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4156635105609894},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3977661728858948},{"id":"https://openalex.org/C24338571","wikidata":"https://www.wikidata.org/wiki/Q2566298","display_name":"Autoregressive integrated moving average","level":3,"score":0.3260136544704437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2944079041481018},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.27310729026794434},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25203168392181396},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.20054590702056885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1761571168899536},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/k19-1084","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k19-1084","pdf_url":"https://www.aclweb.org/anthology/K19-1084.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 23rd Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1909.07063","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.07063","pdf_url":"https://arxiv.org/pdf/1909.07063","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":"text"},{"id":"mag:2972427545","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1909.07063","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.1909.07063","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1909.07063","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":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/k19-1084","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k19-1084","pdf_url":"https://www.aclweb.org/anthology/K19-1084.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 23rd Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2972427545.pdf","grobid_xml":"https://content.openalex.org/works/W2972427545.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W130710483","https://openalex.org/W138349765","https://openalex.org/W1522301498","https://openalex.org/W1821462560","https://openalex.org/W1988857989","https://openalex.org/W2031571562","https://openalex.org/W2061562262","https://openalex.org/W2064675550","https://openalex.org/W2121863487","https://openalex.org/W2130942839","https://openalex.org/W2152808281","https://openalex.org/W2161914416","https://openalex.org/W2311132329","https://openalex.org/W2739473244","https://openalex.org/W2899771611","https://openalex.org/W2906094846","https://openalex.org/W2963403868","https://openalex.org/W2964265128"],"related_works":["https://openalex.org/W3122089380","https://openalex.org/W2903470116","https://openalex.org/W2772692325","https://openalex.org/W2518061732","https://openalex.org/W2981047406","https://openalex.org/W3092636093","https://openalex.org/W3134382996","https://openalex.org/W3122315731","https://openalex.org/W2524433041","https://openalex.org/W2414365285","https://openalex.org/W3201494024","https://openalex.org/W2153116252","https://openalex.org/W2595314642","https://openalex.org/W2943118511","https://openalex.org/W2168822076","https://openalex.org/W2891602259","https://openalex.org/W3006801120","https://openalex.org/W3134641017","https://openalex.org/W2986752238","https://openalex.org/W2963974141"],"abstract_inverted_index":{"Standard":[0],"autoregressive":[1,32,97,136],"seq2seq":[2,23],"models":[3,55],"are":[4],"easily":[5],"trained":[6],"by":[7],"max-likelihood,":[8],"but":[9,75],"tend":[10],"to":[11,46,91],"show":[12,127],"poor":[13],"results":[14],"under":[15,123],"small-data":[16],"conditions.":[17],"We":[18,52],"introduce":[19],"a":[20,35,43,95,128],"class":[21],"of":[22,41,50,72,132],"models,":[24],"GAMs":[25],"(Global":[26],"Autoregressive":[27],"Models),":[28],"which":[29],"combine":[30],"an":[31,65],"component":[33],"with":[34,105],"log-linear":[36],"component,":[37],"allowing":[38],"the":[39,60,70,73,84,101,106,134,139],"use":[40,88],"global":[42],"priori":[44],"features":[45],"compensate":[47],"for":[48,78,112],"lack":[49],"data.":[51],"train":[53,92],"these":[54],"in":[56],"two":[57],"steps.":[58],"In":[59,83],"first":[61],"step,":[62,86],"we":[63,87],"obtain":[64],"unnormalized":[66],"GAM":[67,90],"that":[68,99],"maximizes":[69],"likelihood":[71],"data,":[74],"is":[76],"improper":[77],"fast":[79,113],"inference":[80,114],"or":[81],"evaluation.":[82,116],"second":[85,96,135],"this":[89],"(by":[93],"distillation)":[94],"model":[98,137],"approximates":[100],"normalized":[102],"distribution":[103],"associated":[104],"GAM,":[107],"and":[108,115,126],"can":[109],"be":[110],"used":[111],"Our":[117],"experiments":[118],"focus":[119],"on":[120],"language":[121],"modelling":[122],"synthetic":[124],"conditions":[125],"strong":[129],"perplexity":[130],"reduction":[131],"using":[133],"over":[138],"standard":[140],"one.":[141]},"counts_by_year":[],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}