{"id":"https://openalex.org/W2951471186","doi":"https://doi.org/10.48550/arxiv.1703.08864","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":"2017-03-26","ids":{"openalex":"https://openalex.org/W2951471186","doi":"https://doi.org/10.48550/arxiv.1703.08864","mag":"2951471186"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1703.08864","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.08864","pdf_url":"https://arxiv.org/pdf/1703.08864","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1703.08864","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084332360","display_name":"Alexander G. Ororbia","orcid":"https://orcid.org/0000-0002-2590-1310","observed_orcids":["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":false,"raw_author_name":"Ororbia, Alexander G.","raw_affiliation_strings":["The Pennsylvania State University","College of Information Sciences and Technology, Pennsylvania State University, State College, PA 16802, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]},{"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":"https://orcid.org/0000-0002-6938-5426","observed_orcids":["https://orcid.org/0000-0002-6938-5426"]},"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"]},{"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":["US"],"is_corresponding":false,"raw_author_name":"Mikolov, Tomas","raw_affiliation_strings":["The Pennsylvania State University","Facebook, New York, NY 10003, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Facebook, New York, NY 10003, U.S.A","institution_ids":["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","observed_orcids":["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":false,"raw_author_name":"Reitter, David","raw_affiliation_strings":["The Pennsylvania State University","College of Information Sciences and Technology, Pennsylvania State University, State College, PA 16802, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]},{"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":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6015999913215637,"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":0.6015999913215637,"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":0.12770000100135803,"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":0.09520000219345093,"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/language-modeling","display_name":"language modeling","score":0.8709999918937683},{"id":"https://openalex.org/keywords/long-term-memory","display_name":"long-term memory","score":0.8519999980926514},{"id":"https://openalex.org/keywords/gated-recurrent-neural-networks","display_name":"gated recurrent neural networks","score":0.671999990940094},{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.656000018119812},{"id":"https://openalex.org/keywords/lstm","display_name":"LSTM","score":0.4699999988079071},{"id":"https://openalex.org/keywords/gru","display_name":"GRU","score":0.8830000162124634},{"id":"https://openalex.org/keywords/parameter-efficiency","display_name":"parameter efficiency","score":0.4490000009536743}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8435554504394531},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8286337852478027},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6404430270195007},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6008666753768921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5689811706542969},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.554884135723114},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5510169863700867},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46395936608314514},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4600841999053955},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.4341297745704651},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.396184504032135},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3798716068267822},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18700215220451355},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1703.08864","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.08864","pdf_url":"https://arxiv.org/pdf/1703.08864","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},{"id":"mag:2951471186","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1703.08864","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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.1703.08864","doi":"https://doi.org/10.48550/arxiv.1703.08864","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1703.08864","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"pmh:oai:arXiv.org:1703.08864","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.08864","pdf_url":"https://arxiv.org/pdf/1703.08864","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G7009048037","display_name":"CRII: RI: Alignment in Web-Forum Discourse: Computational Models of Adaptation and Language Change","funder_award_id":"1459300","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"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":44,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W581956982","https://openalex.org/W1522301498","https://openalex.org/W1589104004","https://openalex.org/W1591801644","https://openalex.org/W1632114991","https://openalex.org/W1800356822","https://openalex.org/W1810943226","https://openalex.org/W1924770834","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/W2110485445","https://openalex.org/W2113459411","https://openalex.org/W2115197214","https://openalex.org/W2118776487","https://openalex.org/W2141703670","https://openalex.org/W2149359396","https://openalex.org/W2164418233","https://openalex.org/W2171928131","https://openalex.org/W2207587218","https://openalex.org/W2292877769","https://openalex.org/W2302255633","https://openalex.org/W2319453305","https://openalex.org/W2326533993","https://openalex.org/W2409027918","https://openalex.org/W2469894155","https://openalex.org/W2510842514","https://openalex.org/W2530887700","https://openalex.org/W2556046966","https://openalex.org/W2583687993","https://openalex.org/W2734812719","https://openalex.org/W2781217231","https://openalex.org/W2949117887","https://openalex.org/W2949626814","https://openalex.org/W2951008357","https://openalex.org/W2953061907","https://openalex.org/W2963266340","https://openalex.org/W2964308564","https://openalex.org/W3133056632","https://openalex.org/W4394663752"],"related_works":["https://openalex.org/W2980434023","https://openalex.org/W2952276042","https://openalex.org/W2810658548","https://openalex.org/W2768320620","https://openalex.org/W3130033958","https://openalex.org/W3128207656","https://openalex.org/W3014997656","https://openalex.org/W2790662531","https://openalex.org/W2761286645","https://openalex.org/W2750814024","https://openalex.org/W2891423184","https://openalex.org/W3162668143","https://openalex.org/W2733236492","https://openalex.org/W2613006358","https://openalex.org/W2208299922","https://openalex.org/W2962953733","https://openalex.org/W2962722950","https://openalex.org/W3090334579","https://openalex.org/W2586630418","https://openalex.org/W3110418272"],"abstract_inverted_index":{"Learning":[0],"useful":[1],"information":[2],"across":[3],"long":[4],"time":[5],"lags":[6],"is":[7,41,94,143],"a":[8,42,64,69,82,91],"critical":[9],"and":[10,32,44,68,104,121],"difficult":[11],"problem":[12],"for":[13],"temporal":[14],"neural":[15,52],"models":[16,55],"in":[17],"tasks":[18],"such":[19,113],"as":[20,114],"language":[21,99],"modeling.":[22],"Existing":[23],"architectures":[24],"that":[25,47,146],"address":[26],"the":[27,88,96,102,107,115,122,137,140],"issue":[28],"are":[29],"often":[30],"complex":[31,111,148],"costly":[33],"to":[34,61,132,145],"train.":[35],"The":[36],"Differential":[37],"State":[38],"Framework":[39],"(DSF)":[40],"simple":[43,84],"high-performing":[45],"design":[46],"unifies":[48],"previously":[49],"introduced":[50],"gated":[51,149],"models.":[53],"DSF":[54,89],"maintain":[56],"longer-term":[57],"memory":[58],"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],"This":[75],"requires":[76],"hardly":[77],"any":[78],"more":[79],"parameters":[80],"than":[81],"classical,":[83],"recurrent":[85],"network.":[86],"Within":[87],"framework,":[90],"new":[92],"architecture":[93],"presented,":[95],"Delta-RNN.":[97],"In":[98],"modeling":[100],"at":[101],"word":[103],"character":[105],"levels,":[106],"Delta-RNN":[108],"outperforms":[109],"popular":[110],"architectures,":[112],"Long":[116],"Short":[117],"Term":[118],"Memory":[119],"(LSTM)":[120],"Gated":[123],"Recurrent":[124],"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":2018,"cited_by_count":1}],"updated_date":"2026-10-13T10:08:12.033832","created_date":"2025-10-10T00:00:00"}