{"id":"https://openalex.org/W2559659309","doi":"https://doi.org/10.18653/v1/p17-1030","title":"Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling","display_name":"Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2559659309","doi":"https://doi.org/10.18653/v1/p17-1030","mag":"2559659309"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p17-1030","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-1030","pdf_url":"https://www.aclweb.org/anthology/P17-1030.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P17-1030.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066666034","display_name":"Zhe Gan","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Gan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107893340","display_name":"Chunyuan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunyuan Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102745649","display_name":"Changyou Chen","orcid":"https://orcid.org/0000-0002-3230-2770"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changyou Chen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023417820","display_name":"Yunchen Pu","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunchen Pu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043729465","display_name":"Qinliang Su","orcid":"https://orcid.org/0000-0002-5903-2504"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qinliang Su","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016448581","display_name":"Lawrence Carin","orcid":"https://orcid.org/0000-0001-6277-7948"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lawrence Carin","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5016448581"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"321","last_page":"331"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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":0.790190577507019},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7608577013015747},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7544955015182495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6397272348403931},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6157554984092712},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6125606894493103},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.5764213800430298},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.5697965621948242},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5169517397880554},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.42262494564056396},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.39779359102249146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.790190577507019},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7608577013015747},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7544955015182495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6397272348403931},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6157554984092712},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6125606894493103},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5764213800430298},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.5697965621948242},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5169517397880554},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.42262494564056396},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39779359102249146},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p17-1030","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-1030","pdf_url":"https://www.aclweb.org/anthology/P17-1030.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p17-1030","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-1030","pdf_url":"https://www.aclweb.org/anthology/P17-1030.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2559659309.pdf","grobid_xml":"https://content.openalex.org/works/W2559659309.grobid-xml"},"referenced_works_count":79,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W35527955","https://openalex.org/W68733909","https://openalex.org/W114517082","https://openalex.org/W123701566","https://openalex.org/W179875071","https://openalex.org/W196214544","https://openalex.org/W582134693","https://openalex.org/W1486649854","https://openalex.org/W1522301498","https://openalex.org/W1567512734","https://openalex.org/W1591801644","https://openalex.org/W1592410721","https://openalex.org/W1632114991","https://openalex.org/W1719489212","https://openalex.org/W1810943226","https://openalex.org/W1815076433","https://openalex.org/W1826234144","https://openalex.org/W1836307405","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1904365287","https://openalex.org/W1924770834","https://openalex.org/W1951216520","https://openalex.org/W1956340063","https://openalex.org/W1987937363","https://openalex.org/W1994616650","https://openalex.org/W2014902591","https://openalex.org/W2070246124","https://openalex.org/W2095705004","https://openalex.org/W2101105183","https://openalex.org/W2108677974","https://openalex.org/W2111051539","https://openalex.org/W2114524997","https://openalex.org/W2115701093","https://openalex.org/W2123301721","https://openalex.org/W2144193737","https://openalex.org/W2146502635","https://openalex.org/W2150355110","https://openalex.org/W2154652894","https://openalex.org/W2157331557","https://openalex.org/W2160660844","https://openalex.org/W2162456913","https://openalex.org/W2163455955","https://openalex.org/W2164411961","https://openalex.org/W2165652770","https://openalex.org/W2167433878","https://openalex.org/W2170678468","https://openalex.org/W2185175083","https://openalex.org/W2186210550","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2212703438","https://openalex.org/W2234809627","https://openalex.org/W2238987678","https://openalex.org/W2263490141","https://openalex.org/W2276300401","https://openalex.org/W2292443655","https://openalex.org/W2300605907","https://openalex.org/W2384495648","https://openalex.org/W2431605385","https://openalex.org/W2558834163","https://openalex.org/W2949380545","https://openalex.org/W2950942124","https://openalex.org/W2951266961","https://openalex.org/W2951595529","https://openalex.org/W2952186591","https://openalex.org/W2963153890","https://openalex.org/W2963213121","https://openalex.org/W2963266340","https://openalex.org/W2963736842","https://openalex.org/W2964059111","https://openalex.org/W2964121744","https://openalex.org/W2964325005","https://openalex.org/W4234117503","https://openalex.org/W4297781872","https://openalex.org/W4297797397","https://openalex.org/W6600013530","https://openalex.org/W6600755281"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W2495256954","https://openalex.org/W2259317772"],"abstract_inverted_index":{"Recurrent":[0],"neural":[1],"networks":[2],"(RNNs)":[3],"have":[4],"shown":[5],"promising":[6],"performance":[7],"for":[8,26,33,59],"language":[9],"modeling.":[10],"However,":[11],"traditional":[12],"training":[13,35,61,80],"of":[14,42,83,103,108],"RNNs":[15],"using":[16],"back-propagation":[17],"through":[18],"time":[19],"often":[20],"suffers":[21],"from":[22],"overfitting.":[23],"One":[24],"reason":[25],"this":[27],"is":[28],"that":[29],"stochastic":[30,51,114],"optimization":[31],"(used":[32],"large":[34,60],"sets)":[36,62],"does":[37],"not":[38],"provide":[39],"good":[40],"estimates":[41],"model":[43,88],"uncertainty.":[44],"This":[45],"paper":[46],"leverages":[47],"recent":[48],"advances":[49],"in":[50,67],"gradient":[52,77],"Markov":[53],"Chain":[54],"Monte":[55],"Carlo":[56],"(also":[57],"appropriate":[58],"to":[63,113],"learn":[64],"weight":[65],"uncertainty":[66],"RNNs.":[68],"It":[69],"yields":[70],"a":[71,100],"principled":[72],"Bayesian":[73],"learning":[74],"algorithm,":[75],"adding":[76],"noise":[78],"during":[79],"(enhancing":[81],"exploration":[82],"the":[84,106,109],"model-parameter":[85],"space)":[86],"and":[87,98],"averaging":[89],"when":[90],"testing.":[91],"Extensive":[92],"experiments":[93],"on":[94],"various":[95],"RNN":[96],"models":[97],"across":[99],"broad":[101],"range":[102],"applications":[104],"demonstrate":[105],"superiority":[107],"proposed":[110],"approach":[111],"relative":[112],"optimization.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}