{"id":"https://openalex.org/W3009172038","doi":"https://doi.org/10.1109/tnnls.2020.2975035","title":"Multitask Learning and Reinforcement Learning for Personalized Dialog Generation: An Empirical Study","display_name":"Multitask Learning and Reinforcement Learning for Personalized Dialog Generation: An Empirical Study","publication_year":2020,"publication_date":"2020-03-05","ids":{"openalex":"https://openalex.org/W3009172038","doi":"https://doi.org/10.1109/tnnls.2020.2975035","mag":"3009172038","pmid":"https://pubmed.ncbi.nlm.nih.gov/32149657"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2020.2975035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.2975035","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5083369457","display_name":"Min Yang","orcid":"https://orcid.org/0000-0001-7345-5071"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Min Yang","raw_affiliation_strings":["Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101490859","display_name":"Weiyi Huang","orcid":"https://orcid.org/0009-0000-5271-8194"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiyi Huang","raw_affiliation_strings":["Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056078823","display_name":"Wenting Tu","orcid":"https://orcid.org/0000-0003-1010-7189"},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenting Tu","raw_affiliation_strings":["Shanghai University of Finance and Economics, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai University of Finance and Economics, Shanghai, China","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010974487","display_name":"Qiang Qu","orcid":"https://orcid.org/0000-0001-5814-8460"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Qu","raw_affiliation_strings":["Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074799043","display_name":"Ying Shen","orcid":"https://orcid.org/0000-0002-3220-904X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Shen","raw_affiliation_strings":["School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078920845","display_name":"Kai Lei","orcid":"https://orcid.org/0000-0001-9197-895X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Lei","raw_affiliation_strings":["Peng Cheng Laboratory, PCL Research Center of Networks and Communications, Shenzhen, China","Shenzhen Key Laboratory for Information Centric Networking and Blockchain Technology, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, PCL Research Center of Networks and Communications, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Shenzhen Key Laboratory for Information Centric Networking and Blockchain Technology, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5083369457"],"corresponding_institution_ids":["https://openalex.org/I4210145761"],"apc_list":null,"apc_paid":null,"fwci":4.3898,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.95261161,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"32","issue":"1","first_page":"49","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T12031","display_name":"Speech and dialogue systems","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8752822279930115},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.8674335479736328},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8281794786453247},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.7571918964385986},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6725045442581177},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5073108077049255},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4701547622680664},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4624974727630615},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.46231162548065186},{"id":"https://openalex.org/keywords/personalized-learning","display_name":"Personalized learning","score":0.44910430908203125},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33651310205459595},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.2260608673095703},{"id":"https://openalex.org/keywords/cooperative-learning","display_name":"Cooperative learning","score":0.1037648618221283}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8752822279930115},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.8674335479736328},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8281794786453247},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.7571918964385986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6725045442581177},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5073108077049255},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4701547622680664},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4624974727630615},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.46231162548065186},{"id":"https://openalex.org/C142039133","wikidata":"https://www.wikidata.org/wiki/Q3620943","display_name":"Personalized learning","level":5,"score":0.44910430908203125},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33651310205459595},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2260608673095703},{"id":"https://openalex.org/C51672120","wikidata":"https://www.wikidata.org/wiki/Q303446","display_name":"Cooperative learning","level":3,"score":0.1037648618221283},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C15122004","wikidata":"https://www.wikidata.org/wiki/Q385756","display_name":"Open learning","level":4,"score":0.0},{"id":"https://openalex.org/C88610354","wikidata":"https://www.wikidata.org/wiki/Q1813494","display_name":"Teaching method","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2020.2975035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.2975035","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:32149657","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32149657","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8399999737739563}],"awards":[{"id":"https://openalex.org/G7258111820","display_name":null,"funder_award_id":"Y8G027","funder_id":"https://openalex.org/F4320338153","funder_display_name":"Shenzhen Institutes of Advanced Technology Innovation Program for Excellent Young Researchers"},{"id":"https://openalex.org/G7279263540","display_name":null,"funder_award_id":"61906185","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8777962889","display_name":null,"funder_award_id":"2019A1515011705","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320338153","display_name":"Shenzhen Institutes of Advanced Technology Innovation Program for Excellent Young Researchers","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W10957333","https://openalex.org/W635530177","https://openalex.org/W1810943226","https://openalex.org/W1880262756","https://openalex.org/W1952243512","https://openalex.org/W1999965501","https://openalex.org/W2064675550","https://openalex.org/W2102531443","https://openalex.org/W2117130368","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2140054881","https://openalex.org/W2153579005","https://openalex.org/W2165150801","https://openalex.org/W2176263492","https://openalex.org/W2204302769","https://openalex.org/W2220374841","https://openalex.org/W2251124635","https://openalex.org/W2295072214","https://openalex.org/W2407776548","https://openalex.org/W2462672764","https://openalex.org/W2530901366","https://openalex.org/W2573537087","https://openalex.org/W2578354947","https://openalex.org/W2580382314","https://openalex.org/W2740309605","https://openalex.org/W2765617518","https://openalex.org/W2766869674","https://openalex.org/W2786983967","https://openalex.org/W2800173142","https://openalex.org/W2810821963","https://openalex.org/W2962883855","https://openalex.org/W2963153906","https://openalex.org/W2963167310","https://openalex.org/W2963206148","https://openalex.org/W2963248296","https://openalex.org/W2963371754","https://openalex.org/W2963410018","https://openalex.org/W2963842982","https://openalex.org/W2963864421","https://openalex.org/W2963963856","https://openalex.org/W2963995063","https://openalex.org/W2964065937","https://openalex.org/W2964165364","https://openalex.org/W2964308564","https://openalex.org/W2964352131","https://openalex.org/W2964352247","https://openalex.org/W4214717370","https://openalex.org/W4294170691","https://openalex.org/W4302570325","https://openalex.org/W6600284362","https://openalex.org/W6600426076","https://openalex.org/W6623987585","https://openalex.org/W6638273328","https://openalex.org/W6639619044","https://openalex.org/W6640955601","https://openalex.org/W6675295256","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6682691769","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6685145238","https://openalex.org/W6685322675","https://openalex.org/W6713582272","https://openalex.org/W6722524744","https://openalex.org/W6728038858","https://openalex.org/W6745537681"],"related_works":["https://openalex.org/W2376415519","https://openalex.org/W4294769427","https://openalex.org/W1601381279","https://openalex.org/W1895908943","https://openalex.org/W4225667838","https://openalex.org/W4281893144","https://openalex.org/W2374747083","https://openalex.org/W4388254351","https://openalex.org/W4386270999","https://openalex.org/W2387906841"],"abstract_inverted_index":{"Open-domain":[0],"dialog":[1,24,66,114],"generation,":[2],"which":[3,26],"is":[4,11,153],"a":[5,22,64,112],"crucial":[6],"component":[7],"of":[8,30,44,84,96,139],"artificial":[9],"intelligence,":[10],"an":[12,48],"essential":[13],"and":[14,33,62,73,107,117,190],"challenging":[15],"problem.":[16],"In":[17],"this":[18],"article,":[19],"we":[20],"present":[21],"personalized":[23,37,65,113,158],"system,":[25],"leverages":[27],"the":[28,57,94,120,124,128,137,140,166,174,183],"advantages":[29],"multitask":[31],"learning":[32,35,78,101],"reinforcement":[34,77,100],"for":[36,160],"dialogue":[38],"generation":[39,67,115],"(MRPDG).":[40],"Specifically,":[41],"MRPDG":[42,152],"consists":[43],"two":[45,144],"subtasks:":[46],"1)":[47],"author":[49],"profiling":[50],"module":[51],"that":[52,69,119,151],"recognizes":[53],"user":[54],"characteristics":[55],"from":[56],"input":[58],"sentence":[59],"(auxiliary":[60],"task)":[61],"2)":[63],"system":[68,116],"generates":[70],"informative,":[71],"grammatical,":[72],"coherent":[74],"responses":[75],"with":[76,162],"algorithms":[79],"(primary":[80],"task).":[81],"Three":[82],"kinds":[83],"rewards":[85],"are":[86,133],"proposed":[87,141,167],"to":[88,135,155],"generate":[89],"high-quality":[90,157],"conversations.":[91],"We":[92],"investigate":[93],"effectiveness":[95],"three":[97],"widely":[98],"used":[99],"methods":[102,176],"[i.e.,":[103],"Q-learning,":[104],"policy":[105],"gradient,":[106],"actor-critic":[108],"(AC)":[109],"algorithm]":[110],"in":[111],"demonstrate":[118],"AC":[121],"algorithm":[122],"achieves":[123],"best":[125],"results":[126,149],"on":[127,143],"underlying":[129],"framework.":[130],"Comprehensive":[131],"experiments":[132],"conducted":[134],"evaluate":[136],"performance":[138,172],"model":[142,168],"real-life":[145],"data":[146],"sets.":[147],"Experimental":[148],"illustrate":[150],"able":[154],"produce":[156],"dialogs":[159],"users":[161],"different":[163,178],"characteristics.":[164],"Quantitatively,":[165],"can":[169],"achieve":[170],"better":[171],"than":[173],"compared":[175],"across":[177],"evaluation":[179],"metrics,":[180],"such":[181],"as":[182],"human":[184],"evaluation,":[185],"BiLingual":[186],"Evaluation":[187],"Understudy":[188],"(BLEU),":[189],"perplexity.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
