{"id":"https://openalex.org/W3035084718","doi":"https://doi.org/10.1145/3397271.3401250","title":"GoChat: Goal-oriented Chatbots with Hierarchical Reinforcement Learning","display_name":"GoChat: Goal-oriented Chatbots with Hierarchical Reinforcement Learning","publication_year":2020,"publication_date":"2020-07-25","ids":{"openalex":"https://openalex.org/W3035084718","doi":"https://doi.org/10.1145/3397271.3401250","mag":"3035084718"},"language":"en","primary_location":{"id":"doi:10.1145/3397271.3401250","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"preprint","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/A5100335781","display_name":"Jianfeng Liu","orcid":"https://orcid.org/0000-0003-1505-3888"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianfeng Liu","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087003458","display_name":"Feiyang Pan","orcid":"https://orcid.org/0000-0002-0103-1090"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiyang Pan","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100619435","display_name":"Ling Luo","orcid":"https://orcid.org/0000-0002-5141-0259"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Luo","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100335781"],"corresponding_institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":1.9031,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.88832134,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1793","last_page":"1796"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9926999807357788,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","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"}}],"keywords":[{"id":"https://openalex.org/keywords/chatbot","display_name":"Chatbot","score":0.880113422870636},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.8405478000640869},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8106105327606201},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7141863703727722},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5897879004478455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46422335505485535},{"id":"https://openalex.org/keywords/goal-orientation","display_name":"Goal orientation","score":0.4516838490962982},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.42270219326019287},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38283050060272217},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3211520314216614}],"concepts":[{"id":"https://openalex.org/C2779041454","wikidata":"https://www.wikidata.org/wiki/Q870780","display_name":"Chatbot","level":2,"score":0.880113422870636},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.8405478000640869},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8106105327606201},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7141863703727722},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5897879004478455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46422335505485535},{"id":"https://openalex.org/C84653758","wikidata":"https://www.wikidata.org/wiki/Q5575175","display_name":"Goal orientation","level":2,"score":0.4516838490962982},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.42270219326019287},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38283050060272217},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3211520314216614},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3397271.3401250","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2470673105","https://openalex.org/W2584185835","https://openalex.org/W2604580630","https://openalex.org/W2741363662","https://openalex.org/W2962852262","https://openalex.org/W2962883855","https://openalex.org/W2962896208","https://openalex.org/W2963043030","https://openalex.org/W2963170138","https://openalex.org/W2963206148","https://openalex.org/W2963790827","https://openalex.org/W2963935983","https://openalex.org/W2970799419","https://openalex.org/W3022187094","https://openalex.org/W3098551837"],"related_works":["https://openalex.org/W4383501580","https://openalex.org/W4214931137","https://openalex.org/W4282002136","https://openalex.org/W4362669950","https://openalex.org/W4362670139","https://openalex.org/W3100661441","https://openalex.org/W1995281866","https://openalex.org/W2994392280","https://openalex.org/W4287601611","https://openalex.org/W3161060657"],"abstract_inverted_index":{"A":[0],"chatbot":[1,54],"that":[2],"converses":[3],"like":[4],"a":[5,48,106],"human":[6],"should":[7],"be":[8,11],"goal-oriented":[9,22],"(i.e.,":[10],"purposeful":[12],"in":[13,112],"conversation),":[14],"which":[15,36],"is":[16],"beyond":[17],"language":[18],"generation.":[19],"However,":[20],"existing":[21],"dialogue":[23,63,108],"systems":[24],"often":[25],"heavily":[26],"rely":[27],"on":[28,105,119],"cumbersome":[29],"hand-crafted":[30],"rules":[31],"or":[32],"costly":[33],"labelled":[34],"datasets,":[35],"limits":[37],"the":[38,53,57,73,81,84,88,92,96,121,129,134],"applicability.":[39],"In":[40,101],"this":[41],"paper,":[42],"we":[43],"propose":[44],"Goal-oriented":[45],"Chatbots":[46],"(GoChat),":[47],"framework":[49,66],"for":[50,99,110],"end-to-end":[51],"training":[52],"to":[55,79],"maximize":[56],"long-term":[58],"return":[59],"from":[60],"offline":[61],"multi-turn":[62],"datasets.":[64],"Our":[65],"utilizes":[67],"hierarchical":[68],"reinforcement":[69],"learning":[70],"(HRL),":[71],"where":[72],"high-level":[74],"policy":[75,90],"determines":[76],"some":[77],"sub-goals":[78,93],"guide":[80],"conversation":[82],"towards":[83],"final":[85],"goal,":[86],"and":[87],"low-level":[89],"fulfills":[91],"by":[94],"generating":[95],"corresponding":[97],"utterance":[98],"response.":[100],"our":[102,114],"experiments":[103],"conducted":[104],"real-world":[107],"dataset":[109],"anti-fraud":[111],"financial,":[113],"approach":[115],"outperforms":[116],"previous":[117],"methods":[118],"both":[120],"quality":[122],"of":[123,132],"response":[124],"generation":[125],"as":[126,128],"well":[127],"success":[130],"rate":[131],"accomplishing":[133],"goal.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
