{"id":"https://openalex.org/W2886490473","doi":"https://doi.org/10.1609/aaai.v33i01.33013159","title":"Character-Level Language Modeling with Deeper Self-Attention","display_name":"Character-Level Language Modeling with Deeper Self-Attention","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2886490473","doi":"https://doi.org/10.1609/aaai.v33i01.33013159","mag":"2886490473"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33013159","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013159","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4182/4060","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4182/4060","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025234902","display_name":"Rami Al\u2010Rfou","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":true,"raw_author_name":"Rami Al-Rfou","raw_affiliation_strings":["Google Research","Google Research,"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Research,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044942382","display_name":"Dokook Choe","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":"Dokook Choe","raw_affiliation_strings":["Google","Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090701958","display_name":"Noah Constant","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":"Noah Constant","raw_affiliation_strings":["Google AI","Google AI#TAB#"],"affiliations":[{"raw_affiliation_string":"Google AI","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google AI#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004864409","display_name":"Mandy Guo","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":"Mandy Guo","raw_affiliation_strings":["Google AI","Google AI#TAB#"],"affiliations":[{"raw_affiliation_string":"Google AI","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google AI#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023448834","display_name":"Llion Jones","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":"Llion Jones","raw_affiliation_strings":["Google AI","Google AI#TAB#"],"affiliations":[{"raw_affiliation_string":"Google AI","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google AI#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5025234902"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":5.7161,"has_fulltext":true,"cited_by_count":60,"citation_normalized_percentile":{"value":0.96097973,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"33","issue":"01","first_page":"3159","last_page":"3166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9972000122070312,"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/transformer","display_name":"Transformer","score":0.7956134080886841},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.7919338941574097},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7608507871627808},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.7329983711242676},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7107880711555481},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6362209320068359},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.6178598999977112},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5565170049667358},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5306868553161621},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5146151781082153},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4710630774497986},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4595244526863098},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3543252944946289},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3495256304740906},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.26644301414489746},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08652916550636292},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.07424473762512207},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06681349873542786}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7956134080886841},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.7919338941574097},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7608507871627808},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7329983711242676},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7107880711555481},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6362209320068359},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.6178598999977112},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5565170049667358},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5306868553161621},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5146151781082153},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4710630774497986},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4595244526863098},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3543252944946289},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3495256304740906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26644301414489746},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08652916550636292},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.07424473762512207},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06681349873542786},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1609/aaai.v33i01.33013159","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013159","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4182/4060","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1808.04444","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.04444","pdf_url":"https://arxiv.org/pdf/1808.04444","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:2886490473","is_oa":true,"landing_page_url":"https://www.arxiv.org/pdf/1808.04444","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.1808.04444","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1808.04444","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:10.1609/aaai.v33i01.33013159","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013159","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4182/4060","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2886490473.pdf","grobid_xml":"https://content.openalex.org/works/W2886490473.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1591801644","https://openalex.org/W1836465849","https://openalex.org/W2064675550","https://openalex.org/W2132339004","https://openalex.org/W2150355110","https://openalex.org/W2170240176","https://openalex.org/W2171928131","https://openalex.org/W2175402905","https://openalex.org/W2212703438","https://openalex.org/W2259472270","https://openalex.org/W2282641050","https://openalex.org/W2409027918","https://openalex.org/W2413904250","https://openalex.org/W2418038525","https://openalex.org/W2473934411","https://openalex.org/W2509671015","https://openalex.org/W2510842514","https://openalex.org/W2525246036","https://openalex.org/W2540404261","https://openalex.org/W2553303224","https://openalex.org/W2567070169","https://openalex.org/W2571859396","https://openalex.org/W2589889860","https://openalex.org/W2606347107","https://openalex.org/W2618854269","https://openalex.org/W2619808423","https://openalex.org/W2626778328","https://openalex.org/W2743945814","https://openalex.org/W2757047188","https://openalex.org/W2767406800","https://openalex.org/W2785672818","https://openalex.org/W2786167576","https://openalex.org/W2788760202","https://openalex.org/W2791366550","https://openalex.org/W2798702047","https://openalex.org/W2949117887","https://openalex.org/W2949626814","https://openalex.org/W2950635152","https://openalex.org/W2951008357","https://openalex.org/W2951672049","https://openalex.org/W2951714314","https://openalex.org/W2952136670","https://openalex.org/W2952339051","https://openalex.org/W2953061907","https://openalex.org/W2963304263","https://openalex.org/W3037881859","https://openalex.org/W6607333740","https://openalex.org/W6635446068","https://openalex.org/W6638824847","https://openalex.org/W6666761814","https://openalex.org/W6680532216","https://openalex.org/W6685537299","https://openalex.org/W6701650085","https://openalex.org/W6713098461","https://openalex.org/W6720905350","https://openalex.org/W6732742072","https://openalex.org/W6738195075","https://openalex.org/W6739901393","https://openalex.org/W6748243251"],"related_works":["https://openalex.org/W2963403868","https://openalex.org/W2963341956","https://openalex.org/W2963088785","https://openalex.org/W2911109671","https://openalex.org/W2064675550","https://openalex.org/W2962784628","https://openalex.org/W2940744433","https://openalex.org/W1522301498","https://openalex.org/W2964265128","https://openalex.org/W2964308564","https://openalex.org/W2525778437","https://openalex.org/W2525246036","https://openalex.org/W2787560479","https://openalex.org/W2251939518","https://openalex.org/W2194775991","https://openalex.org/W2101105183","https://openalex.org/W2460550122","https://openalex.org/W2950805620","https://openalex.org/W2949794196","https://openalex.org/W2998873753"],"abstract_inverted_index":{"LSTMs":[0],"and":[1,23,80,106],"other":[2],"RNN":[3,59],"variants":[4,60],"have":[5],"shown":[6],"strong":[7],"performance":[8],"on":[9,70,78,82],"character-level":[10],"language":[11],"modeling.":[12],"These":[13],"models":[14],"are":[15],"typically":[16],"trained":[17],"using":[18],"truncated":[19],"backpropagation":[20],"through":[21],"time,":[22],"it":[24,94],"is":[25,95],"common":[26],"to":[27,36,97],"assume":[28],"that":[29,45,93],"their":[30,34],"success":[31],"stems":[32],"from":[33],"ability":[35],"remember":[37],"long-term":[38],"contexts.":[39],"In":[40],"this":[41,89],"paper,":[42],"we":[43,91],"show":[44,92],"a":[46,62],"deep":[47],"(64-layer)":[48],"transformer":[49],"model":[50],"(Vaswani":[51],"et":[52],"al.":[53],"2017)":[54],"with":[55],"fixed":[56],"context":[57],"outperforms":[58],"by":[61],"large":[63],"margin,":[64],"achieving":[65],"state":[66],"of":[67],"the":[68],"art":[69],"two":[71],"popular":[72],"benchmarks:":[73],"1.13":[74],"bits":[75],"per":[76],"character":[77],"text8":[79],"1.06":[81],"enwik8.":[83],"To":[84],"get":[85],"good":[86],"results":[87],"at":[88,102],"depth,":[90],"important":[96],"add":[98],"auxiliary":[99],"losses,":[100],"both":[101],"intermediate":[103,107],"network":[104],"layers":[105],"sequence":[108],"positions.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}