{"id":"https://openalex.org/W4389987694","doi":"https://doi.org/10.1109/tkde.2023.3344727","title":"Acquiring New Knowledge Without Losing Old Ones for Effective Continual Dialogue Policy Learning","display_name":"Acquiring New Knowledge Without Losing Old Ones for Effective Continual Dialogue Policy Learning","publication_year":2023,"publication_date":"2023-12-20","ids":{"openalex":"https://openalex.org/W4389987694","doi":"https://doi.org/10.1109/tkde.2023.3344727"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2023.3344727","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tkde.2023.3344727","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tkde.2023.3344727","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009639089","display_name":"Huimin Wang","orcid":"https://orcid.org/0000-0002-6147-8310"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huimin Wang","raw_affiliation_strings":["Jarvis Research Center, Tencent YouTu Lab, Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6147-8310","affiliations":[{"raw_affiliation_string":"Jarvis Research Center, Tencent YouTu Lab, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100752462","display_name":"Yunyan Zhang","orcid":"https://orcid.org/0000-0003-1306-5746"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunyan Zhang","raw_affiliation_strings":["Jarvis Research Center, Tencent YouTu Lab, Tencent, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jarvis Research Center, Tencent YouTu Lab, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101646268","display_name":"Yifan Yang","orcid":"https://orcid.org/0000-0003-1891-2246"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Yang","raw_affiliation_strings":["Tencent AI Lab, Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1891-2246","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051649145","display_name":"Yefeng Zheng","orcid":"https://orcid.org/0000-0003-2195-2847"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yefeng Zheng","raw_affiliation_strings":["Jarvis Research Center, Tencent YouTu Lab, Tencent, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jarvis Research Center, Tencent YouTu Lab, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008208316","display_name":"Kam\u2010Fai Wong","orcid":"https://orcid.org/0000-0002-9427-5659"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kam-Fai Wong","raw_affiliation_strings":["Department of System Engineering and Engineering Management, The Chinese University of Hong Kong, Central Ave, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of System Engineering and Engineering Management, The Chinese University of Hong Kong, Central Ave, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6345,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74506866,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"36","issue":"12","first_page":"7569","last_page":"7584"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9868000149726868,"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":0.9868000149726868,"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/T12031","display_name":"Speech and dialogue systems","score":0.9836999773979187,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9735999703407288,"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/forgetting","display_name":"Forgetting","score":0.8970198631286621},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8468184471130371},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6214680075645447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48484623432159424},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4482184648513794},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3739262819290161},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.355202853679657}],"concepts":[{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.8970198631286621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8468184471130371},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6214680075645447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48484623432159424},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4482184648513794},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3739262819290161},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.355202853679657},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2023.3344727","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tkde.2023.3344727","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tkde.2023.3344727","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tkde.2023.3344727","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W62035106","https://openalex.org/W104925946","https://openalex.org/W200223693","https://openalex.org/W1682403713","https://openalex.org/W1950916832","https://openalex.org/W1975244201","https://openalex.org/W1979299372","https://openalex.org/W1986034383","https://openalex.org/W2040123554","https://openalex.org/W2048369091","https://openalex.org/W2107726111","https://openalex.org/W2112259378","https://openalex.org/W2145339207","https://openalex.org/W2151347365","https://openalex.org/W2154740693","https://openalex.org/W2287077337","https://openalex.org/W2347943926","https://openalex.org/W2417401578","https://openalex.org/W2507592741","https://openalex.org/W2560647685","https://openalex.org/W2594726847","https://openalex.org/W2740191615","https://openalex.org/W2765111838","https://openalex.org/W2786446225","https://openalex.org/W2788388592","https://openalex.org/W2788862220","https://openalex.org/W2798494119","https://openalex.org/W2948743095","https://openalex.org/W2949252816","https://openalex.org/W2962717182","https://openalex.org/W2963540014","https://openalex.org/W2963692154","https://openalex.org/W2963797754","https://openalex.org/W2964006684","https://openalex.org/W2964044380","https://openalex.org/W2964048876","https://openalex.org/W2965043358","https://openalex.org/W2965870268","https://openalex.org/W2970828515","https://openalex.org/W2979400990","https://openalex.org/W3015731157","https://openalex.org/W3017258201","https://openalex.org/W3034330559","https://openalex.org/W3035597485","https://openalex.org/W3036362489","https://openalex.org/W3037879762","https://openalex.org/W3048941751","https://openalex.org/W3098511564","https://openalex.org/W3100152912","https://openalex.org/W3104546989","https://openalex.org/W3175994953","https://openalex.org/W3212099586","https://openalex.org/W3214586773","https://openalex.org/W3216055172","https://openalex.org/W4205340316","https://openalex.org/W4283798937","https://openalex.org/W4288287305","https://openalex.org/W4295200480","https://openalex.org/W4312609624","https://openalex.org/W4319988532","https://openalex.org/W6604271302","https://openalex.org/W6696265566","https://openalex.org/W6712392314","https://openalex.org/W6716955619","https://openalex.org/W6725831799","https://openalex.org/W6731835169","https://openalex.org/W6734696739","https://openalex.org/W6738602802","https://openalex.org/W6738741286","https://openalex.org/W6741087337","https://openalex.org/W6742852309","https://openalex.org/W6747481691","https://openalex.org/W6748638692","https://openalex.org/W6755109808","https://openalex.org/W6756754374","https://openalex.org/W6765285020","https://openalex.org/W6775941120","https://openalex.org/W6775959766","https://openalex.org/W6776087331","https://openalex.org/W6803204313","https://openalex.org/W6810936533","https://openalex.org/W6849896277"],"related_works":["https://openalex.org/W4289718052","https://openalex.org/W2164121020","https://openalex.org/W2145559838","https://openalex.org/W3116498279","https://openalex.org/W4287549553","https://openalex.org/W3183027292","https://openalex.org/W2974871044","https://openalex.org/W4310285384","https://openalex.org/W2794885965","https://openalex.org/W3196817267"],"abstract_inverted_index":{"Dialogue":[0],"policy":[1,127,152],"learning":[2],"is":[3,16,190],"the":[4,81,86,90,103,114,121,126,138,164,168,181,187],"core":[5],"decision-making":[6],"module":[7],"of":[8,83,167,186],"a":[9,74,108,150,173],"task-oriented":[10],"dialogue":[11],"system.":[12],"Its":[13],"primary":[14],"objective":[15],"to":[17,20,38,42,54,62,112,116,124,148,154],"assist":[18],"users":[19],"achieve":[21],"their":[22,64],"goals":[23],"effectively":[24],"in":[25,158],"as":[26,29],"few":[27],"turns":[28],"possible.":[30],"A":[31],"practical":[32],"dialogue-policy":[33,58,77],"agent":[34,115],"must":[35],"be":[36],"able":[37],"expand":[39],"its":[40,49],"knowledge":[41],"handle":[43],"new":[44,55],"scenarios":[45],"efficiently":[46],"without":[47],"affecting":[48],"performance.":[50],"Nevertheless,":[51],"when":[52],"adapting":[53],"tasks,":[56],"existing":[57,65],"agents":[59],"often":[60],"fail":[61],"retain":[63,125],"(old)":[66],"knowledge.":[67],"To":[68],"overcome":[69],"this":[70],"predicament,":[71],"we":[72,101,136,171],"propose":[73],"novel":[75],"continual":[76],"model":[78,189],"which":[79,106,141,176],"tackles":[80],"issues":[82],"\u201cnot":[84],"forgetting":[85,104],"old\u201d":[87],"and":[88,194,196],"\u201cacquiring":[89],"new\u201d":[91],"from":[92],"three":[93],"different":[94],"aspects:":[95],"(1)":[96],"For":[97,133,162],"effective":[98],"old-task":[99],"preservation,":[100],"introduce":[102,137,172],"preventor":[105],"uses":[107],"behavior":[109],"cloning":[110],"technique":[111],"force":[113],"take":[117],"actions":[118],"consistent":[119],"with":[120],"replayed":[122,169],"experience":[123],"trained":[128],"on":[129],"historic":[130],"tasks.":[131],"(2)":[132],"new-task":[134],"acquisition,":[135],"adaption":[139],"accelerator":[140],"employs":[142],"an":[143],"invariant":[144],"risk":[145],"minimization":[146],"mechanism":[147],"produce":[149],"stable":[151],"predictor":[153],"avoid":[155],"spurious":[156],"corrections":[157],"training":[159],"data.":[160,183],"(3)":[161],"reducing":[163],"storage":[165],"cost":[166],"experience,":[170],"replay":[174],"manager":[175],"helps":[177],"regularly":[178],"clean":[179],"up":[180],"old":[182],"The":[184],"effectiveness":[185],"proposed":[188],"evaluated":[191],"both":[192],"theoretically":[193],"experimentally":[195],"demonstrated":[197],"favorable":[198],"results.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}