{"id":"https://openalex.org/W4404939347","doi":"https://doi.org/10.1162/tacl_a_00717","title":"Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization","display_name":"Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404939347","doi":"https://doi.org/10.1162/tacl_a_00717"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00717","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00717","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00717/2482041/tacl_a_00717.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00717/2482041/tacl_a_00717.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103015387","display_name":"Yangyang Zhao","orcid":"https://orcid.org/0000-0003-1890-6508"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]},{"id":"https://openalex.org/I56934997","display_name":"Changsha University of Science and Technology","ror":"https://ror.org/03yph8055","country_code":"CN","type":"education","lineage":["https://openalex.org/I56934997"]}],"countries":["CN","NL"],"is_corresponding":false,"raw_author_name":"Yangyang Zhao","raw_affiliation_strings":["Changsha University of Science and Technology, China. yyz@csust.edu.cn","Utrecht University, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Changsha University of Science and Technology, China. yyz@csust.edu.cn","institution_ids":["https://openalex.org/I56934997"]},{"raw_affiliation_string":"Utrecht University, the Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028760842","display_name":"Mehdi Dastani","orcid":"https://orcid.org/0000-0002-4641-4087"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mehdi Dastani","raw_affiliation_strings":["Utrecht University, the Netherlands, M.M.Dastani@uu.nl"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Utrecht University, the Netherlands, M.M.Dastani@uu.nl","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jinchuan Long","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinchuan Long","raw_affiliation_strings":["Central South University, China. longjc1226@163.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University, China. longjc1226@163.com","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100344974","display_name":"Zhenyu Wang","orcid":"https://orcid.org/0000-0002-9815-8775"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Wang","raw_affiliation_strings":["South China University of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107808323","display_name":"Shihan Wang","orcid":"https://orcid.org/0000-0001-5971-7522"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Shihan Wang","raw_affiliation_strings":["Utrecht University, the Netherlands. s.wang2@uu.nl"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Utrecht University, the Netherlands. s.wang2@uu.nl","institution_ids":["https://openalex.org/I193662353"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5107808323"],"corresponding_institution_ids":["https://openalex.org/I139660479","https://openalex.org/I193662353"],"apc_list":null,"apc_paid":null,"fwci":0.4499,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71634772,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"12","issue":null,"first_page":"1578","last_page":"1596"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9987000226974487,"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":0.9987000226974487,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9861000180244446,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9782999753952026,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8097091913223267},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7462759017944336},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4457140266895294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36389124393463135},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33799752593040466},{"id":"https://openalex.org/keywords/management","display_name":"Management","score":0.1008996069431305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8097091913223267},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7462759017944336},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4457140266895294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36389124393463135},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33799752593040466},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.1008996069431305},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1162/tacl_a_00717","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00717","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00717/2482041/tacl_a_00717.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00717","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00717","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00717/2482041/tacl_a_00717.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null},{"id":"https://openalex.org/F4320323059","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404939347.pdf","grobid_xml":"https://content.openalex.org/works/W4404939347.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W385983652","https://openalex.org/W1985713343","https://openalex.org/W2009551863","https://openalex.org/W2051725773","https://openalex.org/W2078011488","https://openalex.org/W2099587687","https://openalex.org/W2107726111","https://openalex.org/W2119717200","https://openalex.org/W2124175081","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2571927164","https://openalex.org/W2740191615","https://openalex.org/W2746553466","https://openalex.org/W2759104452","https://openalex.org/W2765111838","https://openalex.org/W2884814595","https://openalex.org/W2951805158","https://openalex.org/W2962852262","https://openalex.org/W2963140401","https://openalex.org/W2963864421","https://openalex.org/W2963993502","https://openalex.org/W2964006684","https://openalex.org/W2998458199","https://openalex.org/W3023592562","https://openalex.org/W3034330559","https://openalex.org/W3034782127","https://openalex.org/W3038439974","https://openalex.org/W3100790518","https://openalex.org/W3152509363","https://openalex.org/W3170644973","https://openalex.org/W3174681272","https://openalex.org/W3175400354","https://openalex.org/W3175458729","https://openalex.org/W3176706409","https://openalex.org/W3200695557","https://openalex.org/W3207568790","https://openalex.org/W3212099586","https://openalex.org/W4210287384","https://openalex.org/W4300799055","https://openalex.org/W4313703382","https://openalex.org/W4313887415","https://openalex.org/W4367047439","https://openalex.org/W4389009441","https://openalex.org/W6629282427","https://openalex.org/W6678114464","https://openalex.org/W6684921986","https://openalex.org/W6685444567","https://openalex.org/W6731619401","https://openalex.org/W6740801417","https://openalex.org/W6753556266","https://openalex.org/W6758981238","https://openalex.org/W6762823601","https://openalex.org/W6762969092","https://openalex.org/W6810253430"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"Abstract":[0],"Training":[1],"a":[2,44,47,60,67,75,92],"task-oriented":[3],"dialogue":[4,104,112,154],"policy":[5,24],"using":[6],"deep":[7],"reinforcement":[8],"learning":[9,25],"is":[10],"promising":[11],"but":[12],"requires":[13],"extensive":[14],"environment":[15],"exploration.":[16,42],"The":[17],"amount":[18],"of":[19,51,143],"wasted":[20],"invalid":[21,41],"exploration":[22,100],"makes":[23],"inefficient.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30],"define":[31],"and":[32,78,90,97,123,136,141],"argue":[33],"that":[34,82,119],"dead-end":[35,48,61,84,121,133],"states":[36,85,122],"are":[37],"important":[38],"reasons":[39],"for":[40],"When":[43],"conversation":[45],"enters":[46],"state,":[49],"regardless":[50],"the":[52,64,99,126,132,139,144],"actions":[53],"taken":[54],"afterward,":[55],"it":[56],"will":[57],"continue":[58],"in":[59,86],"trajectory":[62],"until":[63],"agent":[65],"reaches":[66],"termination":[68],"state":[69],"or":[70],"maximum":[71],"turn.":[72],"We":[73,129],"propose":[74],"Dead-end":[76],"Detection":[77],"Resurrection":[79],"(DDR)":[80],"method":[81,145],"detects":[83],"an":[87],"efficient":[88],"manner":[89],"provides":[91],"rescue":[93],"action":[94],"to":[95],"guide":[96],"correct":[98],"direction.":[101],"To":[102],"prevent":[103],"policies":[105],"from":[106],"repeating":[107],"errors,":[108],"DDR":[109],"also":[110],"performs":[111],"data":[113],"augmentation":[114],"by":[115],"adding":[116],"relevant":[117],"experiences":[118],"include":[120],"penalties":[124],"into":[125],"experience":[127],"pool.":[128],"first":[130],"validate":[131],"detection":[134],"reliability":[135],"then":[137],"demonstrate":[138],"effectiveness":[140],"generality":[142],"across":[146],"various":[147],"domains":[148],"through":[149],"experiments":[150],"on":[151],"four":[152],"public":[153],"datasets.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}