{"id":"https://openalex.org/W2888693386","doi":"https://doi.org/10.18653/v1/d18-1324","title":"The Importance of Generation Order in Language Modeling","display_name":"The Importance of Generation Order in Language Modeling","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2888693386","doi":"https://doi.org/10.18653/v1/d18-1324","mag":"2888693386"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1324","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1324","pdf_url":"https://www.aclweb.org/anthology/D18-1324.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 2018 Conference on Empirical Methods in Natural Language Processing","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/D18-1324.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089420987","display_name":"Nicolas Ford","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicolas Ford","raw_affiliation_strings":["Google Brain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018358657","display_name":"Daniel Duckworth","orcid":"https://orcid.org/0009-0002-8716-5934"},"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":"Daniel Duckworth","raw_affiliation_strings":["Google Brain","Google (United States), Mountain View, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103947107","display_name":"Mohammad Norouzi","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Norouzi","raw_affiliation_strings":["Google Brain","Google (United States), Mountain View, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047062711","display_name":"George E. Dahl","orcid":"https://orcid.org/0000-0002-0083-844X"},"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":"George Dahl","raw_affiliation_strings":["Google Brain","Google (United States), Mountain View, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2942","last_page":"2946"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":1.0,"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":0.9943000078201294,"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/automatic-summarization","display_name":"Automatic summarization","score":0.8110724687576294},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7831510305404663},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7777714729309082},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.728378415107727},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6032902002334595},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5490572452545166},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5448749661445618},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5393765568733215},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5260529518127441},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4561937749385834},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.43411970138549805},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.4173825681209564},{"id":"https://openalex.org/keywords/structuring","display_name":"Structuring","score":0.4102481007575989},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35582125186920166},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.16417831182479858},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09854400157928467},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08066722750663757}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8110724687576294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7831510305404663},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7777714729309082},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.728378415107727},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6032902002334595},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5490572452545166},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5448749661445618},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5393765568733215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5260529518127441},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4561937749385834},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.43411970138549805},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.4173825681209564},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.4102481007575989},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35582125186920166},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.16417831182479858},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09854400157928467},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08066722750663757},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/d18-1324","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1324","pdf_url":"https://www.aclweb.org/anthology/D18-1324.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1808.07910","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.07910","pdf_url":"https://arxiv.org/pdf/1808.07910","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:2888693386","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1808.07910.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.1808.07910","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1808.07910","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/d18-1324","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1324","pdf_url":"https://www.aclweb.org/anthology/D18-1324.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6800000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2888693386.pdf","grobid_xml":"https://content.openalex.org/works/W2888693386.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2057147815","https://openalex.org/W2259472270","https://openalex.org/W2311132329","https://openalex.org/W2405897494","https://openalex.org/W2525778437","https://openalex.org/W2557321428","https://openalex.org/W2626778328","https://openalex.org/W2798702047","https://openalex.org/W2949237929","https://openalex.org/W2949888546","https://openalex.org/W2953318193","https://openalex.org/W2963754491","https://openalex.org/W2964308564","https://openalex.org/W3198494294"],"related_works":["https://openalex.org/W3191780119","https://openalex.org/W3193875190","https://openalex.org/W3121024243","https://openalex.org/W2124696637","https://openalex.org/W2886026946","https://openalex.org/W2220350356","https://openalex.org/W2902964203","https://openalex.org/W2788982938","https://openalex.org/W2251947680","https://openalex.org/W3211048446","https://openalex.org/W412646894","https://openalex.org/W2196751776","https://openalex.org/W1681397005","https://openalex.org/W3175679307","https://openalex.org/W3083526914","https://openalex.org/W2964011581","https://openalex.org/W2803484822","https://openalex.org/W2137727802","https://openalex.org/W3099038396","https://openalex.org/W3026088249"],"abstract_inverted_index":{"Neural":[0],"language":[1,20,55,121],"models":[2,21],"are":[3,22],"a":[4,33,52,79,112],"critical":[5],"component":[6],"of":[7,44,116],"state-of-the-art":[8],"systems":[9],"for":[10,72,119],"machine":[11],"translation,":[12],"summarization,":[13],"audio":[14],"transcription,":[15],"and":[16,62,77],"other":[17],"tasks.":[18],"These":[19],"almost":[23],"universally":[24],"autoregressive":[25],"in":[26,65,83,95,103],"nature,":[27],"generating":[28],"sentences":[29],"one":[30],"token":[31,45],"at":[32],"time":[34],"from":[35],"left":[36],"to":[37],"right.":[38],"This":[39],"paper":[40],"studies":[41],"the":[42,88,96,104],"influence":[43],"generation":[46,117],"order":[47,118],"on":[48],"model":[49,56,84],"quality":[50],"via":[51],"novel":[53],"two-pass":[54],"that":[57],"produces":[58],"partially-filled":[59],"sentence":[60],"\"templates\"":[61],"then":[63],"fills":[64],"missing":[66],"tokens.":[67],"We":[68,86,106],"compare":[69],"various":[70],"strategies":[71],"structuring":[73],"these":[74,108],"two":[75],"passes":[76],"observe":[78],"surprisingly":[80],"large":[81],"variation":[82],"quality.":[85],"find":[87],"most":[89],"effective":[90],"strategy":[91],"generates":[92],"function":[93],"words":[94,102],"first":[97],"pass":[98],"followed":[99],"by":[100],"content":[101],"second.":[105],"believe":[107],"experimental":[109],"results":[110],"justify":[111],"more":[113],"extensive":[114],"investigation":[115],"neural":[120],"models.":[122]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}