{"id":"https://openalex.org/W4372346229","doi":"https://doi.org/10.1109/icassp49357.2023.10096940","title":"An Asynchronous Updating Reinforcement Learning Framework for Task-Oriented Dialog System","display_name":"An Asynchronous Updating Reinforcement Learning Framework for Task-Oriented Dialog System","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372346229","doi":"https://doi.org/10.1109/icassp49357.2023.10096940"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096940","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100369670","display_name":"Sai Zhang","orcid":"https://orcid.org/0009-0001-4752-6283"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sai Zhang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051919826","display_name":"Yuwei Hu","orcid":"https://orcid.org/0000-0002-0413-5143"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwei Hu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351304","display_name":"Xiaojie Wang","orcid":"https://orcid.org/0000-0003-0314-8951"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086592352","display_name":"Caixia Yuan","orcid":"https://orcid.org/0000-0002-3681-4423"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Caixia Yuan","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100369670"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04079302,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9988999962806702,"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/T12128","display_name":"AI in Service Interactions","score":0.9871000051498413,"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":0.9395241737365723},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.876887321472168},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8278785943984985},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.6959637403488159},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6513513922691345},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5232331156730652},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5032564997673035},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4673939645290375},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39003992080688477},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33753976225852966},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2161063253879547},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.08507674932479858},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08320796489715576}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.9395241737365723},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.876887321472168},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8278785943984985},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.6959637403488159},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6513513922691345},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5232331156730652},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5032564997673035},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4673939645290375},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39003992080688477},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33753976225852966},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2161063253879547},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.08507674932479858},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08320796489715576},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096940","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335577","display_name":"Major Research Plan","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2201581102","https://openalex.org/W2296073425","https://openalex.org/W2736601468","https://openalex.org/W2805406810","https://openalex.org/W2945475330","https://openalex.org/W2964043796","https://openalex.org/W2970828515","https://openalex.org/W2997108628","https://openalex.org/W3017185923","https://openalex.org/W3021016503","https://openalex.org/W3021096583","https://openalex.org/W3034782127","https://openalex.org/W3126192873","https://openalex.org/W3142849873","https://openalex.org/W3175439762","https://openalex.org/W4221141243","https://openalex.org/W4230563027","https://openalex.org/W4287795696","https://openalex.org/W6687681856","https://openalex.org/W6692846177","https://openalex.org/W6741002519","https://openalex.org/W6792244340"],"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/W2920931047"],"abstract_inverted_index":{"Reinforcement":[0,72],"learning":[1,92,105],"has":[2],"been":[3],"applied":[4],"to":[5,95,113],"train":[6,32],"the":[7,16,50,54,61,78,82,97,115,120,137],"dialog":[8,17,51,116,138],"systems":[9],"in":[10],"many":[11],"works.":[12],"Previous":[13],"approaches":[14],"divide":[15],"system":[18,55],"into":[19],"multiple":[20,108],"modules":[21,34,38],"including":[22],"DST":[23,47,62,79],"(dialog":[24,29],"state":[25],"tracking)":[26],"and":[27,31,53,81,107],"DP":[28,83],"policy),":[30],"these":[33],"simultaneously.":[35],"However,":[36],"different":[37],"influence":[39],"each":[40],"other":[41],"during":[42,103],"training.":[43],"The":[44,141],"errors":[45],"from":[46],"might":[48],"misguide":[49],"policy,":[52],"action":[56],"brings":[57],"extra":[58],"difficulties":[59],"for":[60],"module.":[63],"To":[64],"alleviate":[65],"this":[66],"problem,":[67],"we":[68],"propose":[69],"Asynchronous":[70],"Updating":[71],"Learning":[73],"framework":[74],"(AURL)":[75],"that":[76,125],"updates":[77],"module":[80,84],"asynchronously":[85],"under":[86],"a":[87,129,133],"cooperative":[88],"setting.":[89],"Furthermore,":[90],"curriculum":[91],"is":[93,143],"implemented":[94],"address":[96],"problem":[98],"of":[99],"unbalanced":[100],"data":[101],"distribution":[102],"reinforcement":[104],"sampling,":[106],"user":[109],"models":[110],"are":[111],"introduced":[112],"increase":[114],"diversity.":[117],"Results":[118],"on":[119,136],"public":[121],"SSD-PHONE":[122],"dataset":[123],"show":[124],"our":[126],"method":[127],"achieves":[128],"compelling":[130],"result":[131],"with":[132],"31.37%":[134],"improvement":[135],"success":[139],"rate.":[140],"code":[142],"publicly":[144],"available":[145],"via":[146],"https://github.com/shunjiu/AURL.":[147]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}