{"id":"https://openalex.org/W2598933668","doi":"https://doi.org/10.21437/interspeech.2014-561","title":"Feed forward pre-training for recurrent neural network language models","display_name":"Feed forward pre-training for recurrent neural network language models","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2598933668","doi":"https://doi.org/10.21437/interspeech.2014-561","mag":"2598933668"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-561","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-561","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/48827deb-9a49-49e8-92d6-8cf26d14f637","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046462732","display_name":"Siva Reddy Gangireddy","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Siva Reddy Gangireddy","raw_affiliation_strings":["UoE (The University of Edinburgh) : Student"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UoE (The University of Edinburgh) : Student","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108257288","display_name":"Fergus McInnes","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fergus McInnes","raw_affiliation_strings":["University of Edinburgh,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2620","last_page":"2624"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/treebank","display_name":"Treebank","score":0.9642465114593506},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.952864408493042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8822002410888672},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7737393379211426},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7187106609344482},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6491586565971375},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.624008297920227},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.573004424571991},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5575618147850037},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5363392233848572},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4883827567100525},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4419855773448944},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09655925631523132}],"concepts":[{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.9642465114593506},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.952864408493042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8822002410888672},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7737393379211426},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7187106609344482},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6491586565971375},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.624008297920227},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.573004424571991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5575618147850037},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5363392233848572},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4883827567100525},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4419855773448944},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09655925631523132},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2014-561","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-561","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.677.2694","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.677.2694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.inevent-project.eu/files/feed-forward-pre-training-for-recurrent-neural/","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.716.9994","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.716.9994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2014/srg-interspeech14.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/48827deb-9a49-49e8-92d6-8cf26d14f637","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/feed-forward-pretraining-for-recurrent-neural-network-language-models(48827deb-9a49-49e8-92d6-8cf26d14f637).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:openaire/48827deb-9a49-49e8-92d6-8cf26d14f637","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/48827deb-9a49-49e8-92d6-8cf26d14f637","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Gangireddy, S R, McInnes, F & Renals, S 2014, Feed Forward Pre-training for Recurrent Neural Network Language Models. in INTERSPEECH 2014 15th Annual Conference of the International Speech Communication Association. International Speech Communication Association, pp. 2620-2624. < http://www.isca-speech.org/archive/interspeech_2014/i14_2620.html >","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/48827deb-9a49-49e8-92d6-8cf26d14f637","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/48827deb-9a49-49e8-92d6-8cf26d14f637","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Gangireddy, S R, McInnes, F & Renals, S 2014, Feed Forward Pre-training for Recurrent Neural Network Language Models. in INTERSPEECH 2014 15th Annual Conference of the International Speech Communication Association. International Speech Communication Association, pp. 2620-2624. < http://www.isca-speech.org/archive/interspeech_2014/i14_2620.html >","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W101286142","https://openalex.org/W104184427","https://openalex.org/W179875071","https://openalex.org/W400678491","https://openalex.org/W1487724677","https://openalex.org/W1508165687","https://openalex.org/W1601269729","https://openalex.org/W1932968309","https://openalex.org/W1970588407","https://openalex.org/W1970689298","https://openalex.org/W2016589492","https://openalex.org/W2070725064","https://openalex.org/W2107878631","https://openalex.org/W2117278770","https://openalex.org/W2137347187","https://openalex.org/W2150355110","https://openalex.org/W2156718662","https://openalex.org/W2171928131","https://openalex.org/W2172130635","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2739034105","https://openalex.org/W4301800915","https://openalex.org/W2963839582","https://openalex.org/W2964047924","https://openalex.org/W4299838440","https://openalex.org/W2743945814","https://openalex.org/W2962832505","https://openalex.org/W2050138804","https://openalex.org/W2151348424","https://openalex.org/W1494910745"],"abstract_inverted_index":{"The":[0],"recurrent":[1],"neural":[2,47],"network":[3,48],"language":[4,49],"model":[5,50],"(RNNLM)":[6],"has":[7],"been":[8],"demonstrated":[9],"to":[10,70],"consistently":[11],"reduce":[12],"perplexities":[13],"and":[14,99,128],"au-tomatic":[15],"speech":[16],"recognition":[17],"(ASR)":[18],"word":[19,130],"error":[20,131],"rates":[21],"across":[22],"a":[23,32],"variety":[24],"of":[25,43,63,75,82],"domains.":[26],"In":[27],"this":[28],"paper":[29],"we":[30,122],"propose":[31],"pre-training":[33],"method":[34],"for":[35],"the":[36,40,44,53,61,64,72,79,92,103,109,120],"RNNLM,":[37],"by":[38,58],"sharing":[39],"output":[41,73],"weights":[42,62,74],"feed":[45],"forward":[46],"(NNLM)":[51],"with":[52,78],"RNNLM.":[54],"This":[55],"is":[56],"accomplished":[57],"first":[59],"fine-tuning":[60],"NNLM,":[65],"which":[66],"are":[67],"then":[68],"used":[69,107],"initialise":[71],"an":[76],"RNNLM":[77],"same":[80],"number":[81],"hidden":[83],"units.":[84],"We":[85],"have":[86],"carried":[87],"out":[88],"text-based":[89],"experiments":[90,101],"on":[91,102,112],"Penn":[93],"Tree-bank":[94],"Wall":[95],"Street":[96],"Journal":[97],"data,":[98],"ASR":[100,129],"TED":[104],"talks":[105],"data":[106],"in":[108,126],"International":[110],"Workshop":[111],"Spoken":[113],"Language":[114],"Translation":[115],"(IWSLT)":[116],"evaluation":[117],"campaigns.":[118],"Across":[119],"experiments,":[121],"observe":[123],"small":[124],"improvements":[125],"perplexity":[127],"rate.":[132]},"counts_by_year":[{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}