{"id":"https://openalex.org/W2751148689","doi":"https://doi.org/10.1162/neco_a_01017","title":"Learning Simpler Language Models with the Differential State Framework","display_name":"Learning Simpler Language Models with the Differential State Framework","publication_year":2017,"publication_date":"2017-09-28","ids":{"openalex":"https://openalex.org/W2751148689","doi":"https://doi.org/10.1162/neco_a_01017","mag":"2751148689","pmid":"https://pubmed.ncbi.nlm.nih.gov/28957029"},"language":"en","primary_location":{"id":"doi:10.1162/neco_a_01017","is_oa":false,"landing_page_url":"https://doi.org/10.1162/neco_a_01017","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084332360","display_name":"Alexander G. Ororbia","orcid":"https://orcid.org/0000-0002-2590-1310"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alexander G. Ororbia II","raw_affiliation_strings":["College of Information Sciences and Technology, Pennsylvania State University, State College, PA 16802, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Sciences and Technology, Pennsylvania State University, State College, PA 16802, U.S.A","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020917394","display_name":"Tom\u00e1\u0161 Mikolov","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["IL","US"],"is_corresponding":true,"raw_author_name":"Tomas Mikolov","raw_affiliation_strings":["Facebook, New York, NY 10003, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook, New York, NY 10003, U.S.A","institution_ids":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020881468","display_name":"David Reitter","orcid":"https://orcid.org/0000-0002-7887-8257"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Reitter","raw_affiliation_strings":["College of Information Sciences and Technology, Pennsylvania State University, State College, PA 16802, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Sciences and Technology, Pennsylvania State University, State College, PA 16802, U.S.A","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020881468","https://openalex.org/A5020917394","https://openalex.org/A5084332360"],"corresponding_institution_ids":["https://openalex.org/I130769515","https://openalex.org/I2252078561","https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":8.9721,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.98213567,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"29","issue":"12","first_page":"3327","last_page":"3352"},"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":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":0.9879000186920166,"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/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8232946991920471},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7936667203903198},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6628704071044922},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5836499929428101},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.563801109790802},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5179840326309204},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.48686733841896057},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4322599768638611},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4288119077682495},{"id":"https://openalex.org/keywords/reservoir-computing","display_name":"Reservoir computing","score":0.4197515547275543},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41041678190231323},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40158742666244507},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20488685369491577},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07074454426765442}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8232946991920471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7936667203903198},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6628704071044922},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5836499929428101},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.563801109790802},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5179840326309204},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.48686733841896057},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4322599768638611},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4288119077682495},{"id":"https://openalex.org/C135796866","wikidata":"https://www.wikidata.org/wiki/Q7315328","display_name":"Reservoir computing","level":4,"score":0.4197515547275543},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41041678190231323},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40158742666244507},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20488685369491577},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07074454426765442},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/neco_a_01017","is_oa":false,"landing_page_url":"https://doi.org/10.1162/neco_a_01017","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},{"id":"pmid:28957029","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28957029","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural computation","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309370","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W581956982","https://openalex.org/W1505042207","https://openalex.org/W1522301498","https://openalex.org/W1567512734","https://openalex.org/W1589104004","https://openalex.org/W1591801644","https://openalex.org/W1607035479","https://openalex.org/W1632114991","https://openalex.org/W1800356822","https://openalex.org/W1810943226","https://openalex.org/W1815076433","https://openalex.org/W1836465849","https://openalex.org/W1924770834","https://openalex.org/W1959983357","https://openalex.org/W1982370770","https://openalex.org/W2007709031","https://openalex.org/W2027857109","https://openalex.org/W2054125330","https://openalex.org/W2064675550","https://openalex.org/W2086161653","https://openalex.org/W2095705004","https://openalex.org/W2100649405","https://openalex.org/W2106850936","https://openalex.org/W2110485445","https://openalex.org/W2115197214","https://openalex.org/W2118776487","https://openalex.org/W2133564696","https://openalex.org/W2134568112","https://openalex.org/W2141703670","https://openalex.org/W2149359396","https://openalex.org/W2164418233","https://openalex.org/W2171928131","https://openalex.org/W2207587218","https://openalex.org/W2302255633","https://openalex.org/W2319453305","https://openalex.org/W2409027918","https://openalex.org/W2469894155","https://openalex.org/W2530887700","https://openalex.org/W2549046034","https://openalex.org/W2556046966","https://openalex.org/W2559655401","https://openalex.org/W2596272155","https://openalex.org/W2607662938","https://openalex.org/W2781217231","https://openalex.org/W2913059114","https://openalex.org/W2913668833","https://openalex.org/W2951008357","https://openalex.org/W2952276042","https://openalex.org/W2953061907","https://openalex.org/W2962810136","https://openalex.org/W2963703360","https://openalex.org/W2963735467","https://openalex.org/W4212774754","https://openalex.org/W4244712831","https://openalex.org/W4293714597","https://openalex.org/W4297827933","https://openalex.org/W4302375066"],"related_works":["https://openalex.org/W3192662224","https://openalex.org/W2903992663","https://openalex.org/W3008584592","https://openalex.org/W4237814686","https://openalex.org/W2997427060","https://openalex.org/W2953065922","https://openalex.org/W2160451571","https://openalex.org/W2495256954","https://openalex.org/W2259317772","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Learning":[0],"useful":[1],"information":[2],"across":[3],"long":[4,117],"time":[5],"lags":[6],"is":[7,41,82,143],"a":[8,42,64,69,79,94],"critical":[9],"and":[10,32,44,68,105,121],"difficult":[11],"problem":[12],"for":[13],"temporal":[14],"neural":[15,52],"models":[16,55],"in":[17],"tasks":[18],"such":[19,114],"as":[20,115],"language":[21,100],"modeling.":[22],"Existing":[23],"architectures":[24],"that":[25,47,146],"address":[26],"the":[27,76,84,103,108,116,122,137,140],"issue":[28],"are":[29],"often":[30],"complex":[31,112,148],"costly":[33],"to":[34,61,132,145],"train.":[35],"The":[36],"differential":[37],"state":[38],"framework":[39],"(DSF)":[40],"simple":[43,96],"high-performing":[45],"design":[46],"unifies":[48],"previously":[49],"introduced":[50],"gated":[51,123,149],"models.":[53],"DSF":[54,77],"maintain":[56],"longer-term":[57],"memory":[58,119],"by":[59],"learning":[60],"interpolate":[62],"between":[63],"fast-changing":[65],"data-driven":[66],"representation":[67],"slowly":[70],"changing,":[71],"implicitly":[72],"stable":[73],"state.":[74],"Within":[75],"framework,":[78],"new":[80],"architecture":[81],"presented,":[83],"delta-RNN.":[85],"This":[86],"model":[87],"requires":[88],"hardly":[89],"any":[90],"more":[91],"parameters":[92],"than":[93],"classical,":[95],"recurrent":[97,124],"network.":[98],"In":[99],"modeling":[101],"at":[102],"word":[104],"character":[106],"levels,":[107],"delta-RNN":[109],"outperforms":[110],"popular":[111],"architectures,":[113],"short-term":[118],"(LSTM)":[120],"unit":[125],"(GRU),":[126],"and,":[127],"when":[128],"regularized,":[129],"performs":[130],"comparably":[131],"several":[133],"state-of-the-art":[134],"baselines.":[135],"At":[136],"subword":[138],"level,":[139],"delta-RNN's":[141],"performance":[142],"comparable":[144],"of":[147],"architectures.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}