{"id":"https://openalex.org/W4406458726","doi":"https://doi.org/10.1109/bigdata62323.2024.10825582","title":"Improving Multi-Domain Task-Oriented Dialogue System with Offline Reinforcement Learning","display_name":"Improving Multi-Domain Task-Oriented Dialogue System with Offline Reinforcement Learning","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406458726","doi":"https://doi.org/10.1109/bigdata62323.2024.10825582"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5114653493","display_name":"Dharmendra Prajapat","orcid":null},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Dharmendra Prajapat","raw_affiliation_strings":["Indian Institute of Technology,Dept of Computer Science and Engineering,Roorkee,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Dept of Computer Science and Engineering,Roorkee,India","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082753354","display_name":"Durga Toshniwal","orcid":null},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Durga Toshniwal","raw_affiliation_strings":["Indian Institute of Technology,Dept of Computer Science and Engineering,Roorkee,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Dept of Computer Science and Engineering,Roorkee,India","institution_ids":["https://openalex.org/I154851008"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5114653493"],"corresponding_institution_ids":["https://openalex.org/I154851008"],"apc_list":null,"apc_paid":null,"fwci":0.7232,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78406061,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2013","last_page":"2018"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T12031","display_name":"Speech and dialogue systems","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/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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":0.994700014591217,"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":0.822817325592041},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7720435857772827},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6542579531669617},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5359433889389038},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.43318891525268555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41600337624549866},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10119155049324036},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.08768361806869507}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.822817325592041},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7720435857772827},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6542579531669617},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5359433889389038},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43318891525268555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41600337624549866},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10119155049324036},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.08768361806869507},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1598178035","https://openalex.org/W1948566616","https://openalex.org/W1975244201","https://openalex.org/W2101105183","https://openalex.org/W2156517809","https://openalex.org/W2783549597","https://openalex.org/W2896457183","https://openalex.org/W2962715022","https://openalex.org/W2964006684","https://openalex.org/W2979520138","https://openalex.org/W2997108628","https://openalex.org/W3034533785","https://openalex.org/W3098807778","https://openalex.org/W3135001991","https://openalex.org/W3156697766","https://openalex.org/W3201659492","https://openalex.org/W3214585123","https://openalex.org/W4287795696","https://openalex.org/W4288089799","https://openalex.org/W4294974598","https://openalex.org/W4307900381","https://openalex.org/W6747724447","https://openalex.org/W6769627184","https://openalex.org/W6771489201","https://openalex.org/W6776587266","https://openalex.org/W6791256585","https://openalex.org/W6841791078"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"Task-oriented":[0],"dialogue":[1],"(TOD)":[2],"system":[3,14,62,91,158,161],"is":[4,76,101,141],"designed":[5],"to":[6,36,184],"accomplish":[7],"user-defined":[8],"tasks":[9],"through":[10],"dialogues.":[11],"The":[12,86,99,115],"TOD":[13,61,90],"has":[15],"progressed":[16],"towards":[17],"end-to-end":[18],"modeling":[19],"by":[20,143,175,181],"leveraging":[21],"pre-trained":[22,28,67,146],"large":[23],"language":[24,29,68,126],"models.":[25],"Fine-tuning":[26],"the":[27,37,47,51,89,104,108,125,149,172,178,185],"models":[30,48],"using":[31,78,94,103],"only":[32],"supervised":[33,79],"learning":[34,80,84],"leads":[35],"exposure":[38],"bias":[39],"and":[40,44,81,111,118,136,160,177],"token":[41],"loss":[42],"problem":[43],"it":[45],"deviates":[46],"from":[49],"completing":[50],"user\u2019s":[52],"task.":[53],"To":[54],"address":[55],"these":[56],"issues,":[57],"we":[58],"propose":[59],"a":[60,65,72,95,134,145],"that":[63,168],"leverages":[64],"unified":[66],"model,":[69],"GPT-2,":[70],"as":[71],"base":[73],"model.":[74],"It":[75],"optimized":[77],"offline":[82],"reinforcement":[83],"(RL).":[85],"issues":[87],"in":[88,121],"are":[92],"mitigated":[93],"non-differentiable":[96],"reward":[97,100,122],"function.":[98],"calculated":[102],"weighted":[105],"sum":[106],"of":[107],"success":[109,116,179],"rate":[110,117,174,180],"BLEU":[112,119],"evaluation":[113],"metrics.":[114],"metrics":[120],"calculation":[123],"guide":[124],"model":[127,140,147,170],"for":[128],"user":[129,154],"task":[130],"completion":[131],"while":[132],"ensuring":[133],"coherent":[135],"fluent":[137],"response.":[138,162],"Our":[139],"acquired":[142],"fine-tuning":[144],"on":[148,165],"dialogue-session":[150],"level":[151],"which":[152],"comprises":[153],"utterance,":[155],"belief":[156],"state,":[157],"act,":[159],"Experimental":[163],"results":[164],"MultiWOZ2.1":[166],"demonstrate":[167],"our":[169],"increases":[171],"inform":[173],"1.60%":[176],"3.17%":[182],"compared":[183],"baseline.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}