{"id":"https://openalex.org/W3119055366","doi":null,"title":"Refine and Imitate: Reducing Repetition and Inconsistency in Dialogue Generation via Reinforcement Learning and Human Demonstration","display_name":"Refine and Imitate: Reducing Repetition and Inconsistency in Dialogue Generation via Reinforcement Learning and Human Demonstration","publication_year":2021,"publication_date":"2021-05-04","ids":{"openalex":"https://openalex.org/W3119055366","mag":"3119055366"},"language":"en","primary_location":{"id":"mag:3119055366","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=JthLaV0RsV","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5089522357","display_name":"Weiyan Shi","orcid":"https://orcid.org/0000-0003-0850-5831","observed_orcids":["https://orcid.org/0000-0003-0850-5831"]},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiyan Shi","raw_affiliation_strings":["Univ. of California Davis"],"raw_orcid":"https://orcid.org/0000-0003-0850-5831","affiliations":[{"raw_affiliation_string":"Univ. of California Davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yu Li","orcid":"https://orcid.org/0000-0002-3664-6722","observed_orcids":["https://orcid.org/0000-0002-3664-6722"]},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Li","raw_affiliation_strings":["Univ. of California Davis"],"raw_orcid":"https://orcid.org/0000-0002-3664-6722","affiliations":[{"raw_affiliation_string":"Univ. of California Davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113347067","display_name":"Saurav Sahay","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurav Sahay","raw_affiliation_strings":["Intel,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel,,,,,","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101815945","display_name":"Zhou Yu","orcid":"https://orcid.org/0000-0002-1524-5890","observed_orcids":["https://orcid.org/0000-0002-1524-5890"]},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou Yu","raw_affiliation_strings":["Univ. of California Davis"],"raw_orcid":"https://orcid.org/0000-0002-1524-5890","affiliations":[{"raw_affiliation_string":"Univ. of California Davis","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00570479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":1.0,"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":1.0,"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":0.0,"subfield":{"id":"https://openalex.org/subfields/1406","display_name":"Marketing"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.0,"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/dialogue-generation","display_name":"dialogue generation","score":0.8579999804496765},{"id":"https://openalex.org/keywords/repetition-reduction","display_name":"repetition reduction","score":0.8399999737739563},{"id":"https://openalex.org/keywords/response-consistency","display_name":"response consistency","score":0.7730000019073486},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.7580000162124634},{"id":"https://openalex.org/keywords/human-demonstrations","display_name":"human demonstrations","score":0.824999988079071},{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.6769999861717224},{"id":"https://openalex.org/keywords/persuasion","display_name":"persuasion","score":0.7630000114440918},{"id":"https://openalex.org/keywords/persuasive-dialogue","display_name":"persuasive dialogue","score":0.5950000286102295},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7020000219345093},{"id":"https://openalex.org/keywords/reward-function-design","display_name":"reward function design","score":0.6549999713897705}],"concepts":[{"id":"https://openalex.org/C2781310500","wikidata":"https://www.wikidata.org/wiki/Q1231428","display_name":"Persuasion","level":2,"score":0.7642312049865723},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7471047639846802},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6536193490028381},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5553054809570312},{"id":"https://openalex.org/C2776141515","wikidata":"https://www.wikidata.org/wiki/Q1274479","display_name":"Repetition (rhetorical device)","level":2,"score":0.5343771576881409},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5291624069213867},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5137001276016235},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5136772990226746},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4986231327056885},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4813550114631653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46970173716545105},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43927937746047974},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4213646352291107},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36622464656829834},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.21216970682144165},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14954262971878052},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.13205358386039734},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3119055366","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=JthLaV0RsV","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3116890199","https://openalex.org/W2963712524","https://openalex.org/W4387425103","https://openalex.org/W4367310790","https://openalex.org/W4226227457","https://openalex.org/W3035068109","https://openalex.org/W7132847011","https://openalex.org/W3022327347","https://openalex.org/W2983160116","https://openalex.org/W4306294747"],"abstract_inverted_index":{"Despite":[0],"the":[1,13,33,39,94,97,112,149,155],"recent":[2],"success":[3],"of":[4],"large-scale":[5],"language":[6,34,72],"models":[7,125],"on":[8,46,126,134],"various":[9],"downstream":[10],"NLP":[11],"tasks,":[12],"repetition":[14,30],"and":[15,49,55,77,84,110,130,139,144,157],"inconsistency":[16,83],"problems":[17],"still":[18],"persist":[19],"in":[20,38],"dialogue":[21,95,124],"response":[22],"generation.":[23],"Previous":[24],"approaches":[25],"have":[26],"attempted":[27],"to":[28,52,64,68,91,103,148],"avoid":[29],"by":[31],"penalizing":[32],"model's":[35],"undesirable":[36],"behaviors":[37],"loss":[40],"function.":[41],"However,":[42],"these":[43,60],"methods":[44],"focus":[45],"token-level":[47],"information":[48,80],"can":[50],"lead":[51],"incoherent":[53],"responses":[54],"uninterpretable":[56],"behaviors.":[57],"To":[58],"alleviate":[59],"issues,":[61],"we":[62],"propose":[63],"apply":[65],"reinforcement":[66],"learning":[67],"refine":[69],"an":[70],"MLE-based":[71],"model":[73,98,120],"without":[74],"user":[75,150],"simulators,":[76],"distill":[78],"sentence-level":[79],"about":[81],"repetition,":[82],"task":[85],"relevance":[86],"through":[87],"rewards.":[88],"In":[89],"addition,":[90],"better":[92],"accomplish":[93],"task,":[96,138],"learns":[99],"from":[100],"human":[101,131],"demonstration":[102],"imitate":[104],"intellectual":[105],"activities":[106],"such":[107],"as":[108],"persuasion,":[109],"selects":[111],"most":[113],"persuasive":[114,145],"responses.":[115],"Experiments":[116],"show":[117],"that":[118],"our":[119],"outperforms":[121],"previous":[122],"state-of-the-art":[123],"both":[127],"automatic":[128],"metrics":[129],"evaluation":[132],"results":[133],"a":[135],"donation":[136],"persuasion":[137],"generates":[140],"more":[141],"diverse,":[142],"consistent":[143],"conversations":[146],"according":[147],"feedback.":[151],"We":[152],"will":[153],"release":[154],"code":[156],"data":[158],"upon":[159],"acceptance.":[160]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2021-01-18T00:00:00"}