{"id":"https://openalex.org/W4285606547","doi":"https://doi.org/10.24963/ijcai.2022/626","title":"\u201cThink Before You Speak\u201d: Improving Multi-Action Dialog Policy by Planning Single-Action Dialogs","display_name":"\u201cThink Before You Speak\u201d: Improving Multi-Action Dialog Policy by Planning Single-Action Dialogs","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285606547","doi":"https://doi.org/10.24963/ijcai.2022/626"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/626","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/626","pdf_url":"https://www.ijcai.org/proceedings/2022/0626.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0626.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102955797","display_name":"Shuo Zhang","orcid":"https://orcid.org/0009-0007-0282-8388"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuo Zhang","raw_affiliation_strings":["Xi'an Jiaotong University","MOE KLINNS Lab, Xi'an Jiaotong University, Xi'an 710049, P. R. China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"MOE KLINNS Lab, Xi'an Jiaotong University, Xi'an 710049, P. R. China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007402211","display_name":"Junzhou Zhao","orcid":"https://orcid.org/0000-0003-3476-8248"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junzhou Zhao","raw_affiliation_strings":["Xi'an Jiaotong University","MOE KLINNS Lab, Xi'an Jiaotong University, Xi'an 710049, P. R. China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"MOE KLINNS Lab, Xi'an Jiaotong University, Xi'an 710049, P. R. China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102845337","display_name":"Pinghui Wang","orcid":"https://orcid.org/0000-0002-1434-837X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pinghui Wang","raw_affiliation_strings":["Xi'an Jiaotong University","MOE KLINNS Lab, Xi'an Jiaotong University, Xi'an 710049, P. R. China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"MOE KLINNS Lab, Xi'an Jiaotong University, Xi'an 710049, P. R. China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053820874","display_name":"Li Yu","orcid":"https://orcid.org/0000-0001-6033-7703"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Li","raw_affiliation_strings":["Xi\u2019an Jiaotong University","MOE KLINNS Lab, Xi'an Jiaotong University, Xi'an 710049, P. R. China"],"affiliations":[{"raw_affiliation_string":"Xi\u2019an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"MOE KLINNS Lab, Xi'an Jiaotong University, Xi'an 710049, P. R. China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100741266","display_name":"Yi Huang","orcid":"https://orcid.org/0000-0002-8443-6877"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Huang","raw_affiliation_strings":["China Mobile Research","JIUTIAN Team, China Mobile Research, Beijing 100053, P. R. China"],"affiliations":[{"raw_affiliation_string":"China Mobile Research","institution_ids":["https://openalex.org/I180662265"]},{"raw_affiliation_string":"JIUTIAN Team, China Mobile Research, Beijing 100053, P. R. China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079750750","display_name":"Junlan Feng","orcid":"https://orcid.org/0000-0001-5292-2945"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlan Feng","raw_affiliation_strings":["China Mobile Research","JIUTIAN Team, China Mobile Research, Beijing 100053, P. R. China"],"affiliations":[{"raw_affiliation_string":"China Mobile Research","institution_ids":["https://openalex.org/I180662265"]},{"raw_affiliation_string":"JIUTIAN Team, China Mobile Research, Beijing 100053, P. R. China","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102955797"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.1048,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.26743693,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4510","last_page":"4516"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9993000030517578,"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/T12128","display_name":"AI in Service Interactions","score":0.9923999905586243,"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":0.9811697006225586},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8523435592651367},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7057133316993713},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.7031140327453613},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6554712653160095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5822943449020386},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5472034215927124},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.5197243690490723},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.43634361028671265},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.42075997591018677},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.40049654245376587},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39296385645866394},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3322314918041229},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18066024780273438},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09320122003555298}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.9811697006225586},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8523435592651367},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7057133316993713},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7031140327453613},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6554712653160095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5822943449020386},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5472034215927124},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.5197243690490723},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.43634361028671265},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.42075997591018677},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40049654245376587},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39296385645866394},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3322314918041229},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18066024780273438},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09320122003555298},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/626","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/626","pdf_url":"https://www.ijcai.org/proceedings/2022/0626.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/626","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/626","pdf_url":"https://www.ijcai.org/proceedings/2022/0626.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2126049948","display_name":null,"funder_award_id":"61902305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2981938667","display_name":null,"funder_award_id":"Shenzhen","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3448220895","display_name":null,"funder_award_id":"161008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3757194791","display_name":null,"funder_award_id":"JCYJ20","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4796592722","display_name":null,"funder_award_id":"61922067","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5641397543","display_name":null,"funder_award_id":"201708","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6741091021","display_name":null,"funder_award_id":"6192206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285606547.pdf","grobid_xml":"https://content.openalex.org/works/W4285606547.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2547875792","https://openalex.org/W2736601468","https://openalex.org/W2798494119","https://openalex.org/W2806936550","https://openalex.org/W2889186204","https://openalex.org/W2949252816","https://openalex.org/W2963095800","https://openalex.org/W2963433587","https://openalex.org/W2964006684","https://openalex.org/W2970828515","https://openalex.org/W2997771882","https://openalex.org/W3006978394","https://openalex.org/W3034656193","https://openalex.org/W3034930293","https://openalex.org/W3035597485","https://openalex.org/W3037879762","https://openalex.org/W3088273075","https://openalex.org/W3099605929","https://openalex.org/W3105781833","https://openalex.org/W3111911316","https://openalex.org/W3123450617","https://openalex.org/W3124798551","https://openalex.org/W4288245792"],"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":{"Multi-action":[0],"dialog":[1,8,18,38,49,102],"policy":[2],"(MADP),":[3],"which":[4],"generates":[5],"multiple":[6],"atomic":[7],"actions":[9],"per":[10],"turn,":[11],"has":[12],"been":[13],"widely":[14],"applied":[15,60],"in":[16],"task-oriented":[17],"systems":[19],"to":[20,41,61,77,104,117,152],"provide":[21],"expressive":[22],"and":[23,54,69,79,159],"efficient":[24],"system":[25],"responses.":[26],"Existing":[27],"MADP":[28],"models":[29],"usually":[30],"imitate":[31],"action":[32],"combinations":[33],"from":[34,81,168],"the":[35,121,131,153,160],"labeled":[36],"multi-action":[37,106],"samples.":[39],"Due":[40],"data":[42,64],"limitations,":[43],"they":[44,72],"generalize":[45],"poorly":[46],"toward":[47],"unseen":[48],"flows.":[50],"While":[51],"interactive":[52],"learning":[53,56,97],"reinforcement":[55],"algorithms":[57],"can":[58,165],"be":[59,166],"incorporate":[62],"external":[63],"sources":[65],"of":[66,147,162],"real":[67],"users":[68],"user":[70],"simulators,":[71],"take":[73],"significant":[74],"manual":[75],"effort":[76],"build":[78],"suffer":[80],"instability.":[82],"To":[83],"address":[84],"these":[85],"issues,":[86],"we":[87],"propose":[88],"Planning":[89],"Enhanced":[90],"Dialog":[91],"Policy":[92],"(PEDP),":[93],"a":[94,142],"novel":[95],"multi-task":[96],"framework":[98],"that":[99,135],"learns":[100],"single-action":[101,126],"dynamics":[103],"enhance":[105],"prediction.":[107],"Our":[108],"PEDP":[109],"method":[110,140],"employs":[111],"model-based":[112],"planning":[113],"for":[114],"conceiving":[115],"what":[116],"express":[118],"before":[119],"deciding":[120],"current":[122],"response":[123],"through":[124],"simulating":[125],"dialogs.":[127],"Experimental":[128],"results":[129],"on":[130],"MultiWOZ":[132],"dataset":[133],"demonstrate":[134],"our":[136],"fully":[137],"supervised":[138],"learning-based":[139],"achieves":[141],"solid":[143],"task":[144],"success":[145],"rate":[146],"90.6%,":[148],"improving":[149],"3%":[150],"compared":[151],"state-of-the-art":[154],"methods.":[155],"The":[156],"source":[157],"code":[158],"appendix":[161],"this":[163],"paper":[164],"obtained":[167],"https://github.com/ShuoZhangXJTU/PEDP.":[169]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}