{"id":"https://openalex.org/W2092896632","doi":"https://doi.org/10.1109/slt.2012.6424160","title":"Simultaneous feature selection and parameter optimization for training of dialog policy by reinforcement learning","display_name":"Simultaneous feature selection and parameter optimization for training of dialog policy by reinforcement learning","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2092896632","doi":"https://doi.org/10.1109/slt.2012.6424160","mag":"2092896632"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2012.6424160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5084637778","display_name":"Teruhisa Misu","orcid":"https://orcid.org/0000-0002-6398-9245"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Teruhisa Misu","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan","National Institute of Information and Communications Technology (NiCT), Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology (NiCT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108760549","display_name":"Hideki Kashioka","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideki Kashioka","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan","National Institute of Information and Communications Technology (NiCT), Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology (NiCT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5084637778"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":1.5158068,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.86554741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T12031","display_name":"Speech and dialogue systems","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/T10028","display_name":"Topic Modeling","score":0.9975000023841858,"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":0.9973000288009644,"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/dialog-box","display_name":"Dialog box","score":0.9698803424835205},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.895720362663269},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.8622161746025085},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7939972877502441},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.687981367111206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6440243721008301},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5916275978088379},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5838559865951538},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48858532309532166},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48629531264305115},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.46548357605934143},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0697050392627716}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.9698803424835205},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.895720362663269},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.8622161746025085},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7939972877502441},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.687981367111206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6440243721008301},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5916275978088379},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5838559865951538},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48858532309532166},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48629531264305115},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.46548357605934143},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0697050392627716},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"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":1,"locations":[{"id":"doi:10.1109/slt.2012.6424160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W27627492","https://openalex.org/W178897730","https://openalex.org/W1211946649","https://openalex.org/W1510109275","https://openalex.org/W1778387566","https://openalex.org/W1974821254","https://openalex.org/W2016357801","https://openalex.org/W2021151961","https://openalex.org/W2084709792","https://openalex.org/W2100495367","https://openalex.org/W2118120353","https://openalex.org/W2118858186","https://openalex.org/W2126152565","https://openalex.org/W2142831953","https://openalex.org/W2151904921","https://openalex.org/W2172968643","https://openalex.org/W4214717370","https://openalex.org/W6637924565","https://openalex.org/W6644185902","https://openalex.org/W6677919164","https://openalex.org/W6678716579"],"related_works":["https://openalex.org/W48079147","https://openalex.org/W2394821827","https://openalex.org/W2563921006","https://openalex.org/W1963944933","https://openalex.org/W1600043506","https://openalex.org/W2174703168","https://openalex.org/W2111550420","https://openalex.org/W2549666521","https://openalex.org/W3133893348","https://openalex.org/W3133451788"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,9,14,26,29,35,39,44,50,54,58,78,85,88,102,114,118,136,140,155,161],"problem":[4],"of":[5,13,17,65,87,104,113],"feature":[6,98,119,164],"selection":[7,79,99,120,165],"in":[8,110,125,168],"reinforcement":[10],"learning":[11,156],"(RL)":[12],"dialog":[15,19,23,41,59,89,106,115,126,147],"policies":[16],"spoken":[18],"systems.":[20],"A":[21],"statistical":[22],"manager":[24],"selects":[25],"system":[27,30,55],"actions":[28],"should":[31,80],"take":[32],"based":[33],"on":[34],"features":[36,51,68],"derived":[37],"from":[38,69],"current":[40],"state":[42],"and/or":[43],"system's":[45],"belief":[46],"state.":[47],"When":[48],"defining":[49],"used":[52],"by":[53,108,129],"for":[56,101],"training":[57],"policy,":[60],"however,":[61],"finding":[62],"a":[63,105,132,145],"set":[64],"actually":[66],"effective":[67],"potentially":[70],"useful":[71],"ones":[72],"is":[73,158,166],"not":[74],"obvious.":[75],"In":[76,91],"addition,":[77],"be":[81],"done":[82],"simultaneously":[83],"with":[84,131,149,160],"optimization":[86,103,128],"policy.":[90],"this":[92],"paper,":[93],"we":[94],"propose":[95],"an":[96],"incremental":[97],"method":[100,142],"policy":[107,116,127,148,151],"RL,":[109],"which":[111],"improvement":[112],"and":[117,153],"are":[121],"conducted":[122,167],"simultaneously.":[123],"Experiments":[124],"RL":[130],"user":[133],"simulator":[134],"demonstrated":[135],"following:":[137],"1)":[138],"that":[139],"proposed":[141],"can":[143],"find":[144],"better":[146],"fewer":[150],"iterations":[152],"2)":[154],"speed":[157],"comparable":[159],"case":[162],"where":[163],"advance.":[169]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}