{"id":"https://openalex.org/W2965033324","doi":"https://doi.org/10.24963/ijcai.2019/711","title":"A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer","display_name":"A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2965033324","doi":"https://doi.org/10.24963/ijcai.2019/711","mag":"2965033324"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/711","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/711","pdf_url":"https://www.ijcai.org/proceedings/2019/0711.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0711.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019525050","display_name":"Fuli Luo","orcid":"https://orcid.org/0000-0002-5403-6434"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuli Luo","raw_affiliation_strings":["Key Lab of Computational Linguistics, School of EECS, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Lab of Computational Linguistics, School of EECS, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432725","display_name":"Peng Li","orcid":"https://orcid.org/0000-0002-7138-430X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Li","raw_affiliation_strings":["Pattern Recognition Center, WeChat AI, Tencent Inc, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition Center, WeChat AI, Tencent Inc, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770464","display_name":"Jie Zhou","orcid":"https://orcid.org/0000-0002-5899-5165"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhou","raw_affiliation_strings":["Pattern Recognition Center, WeChat AI, Tencent Inc, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition Center, WeChat AI, Tencent Inc, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063385901","display_name":"Pengcheng Yang","orcid":"https://orcid.org/0000-0001-8671-9523"},"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/I4210096250","display_name":"Beijing Institute of Big Data Research","ror":"https://ror.org/00s1sz824","country_code":"CN","type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I37796252","https://openalex.org/I4210096250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Yang","raw_affiliation_strings":["Deep Learning Lab, Beijing Institute of Big Data Research, Peking University","Key Lab of Computational Linguistics, School of EECS, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deep Learning Lab, Beijing Institute of Big Data Research, Peking University","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210096250"]},{"raw_affiliation_string":"Key Lab of Computational Linguistics, School of EECS, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021459300","display_name":"Baobao Chang","orcid":"https://orcid.org/0000-0003-2824-6750"},"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":"Baobao Chang","raw_affiliation_strings":["Key Lab of Computational Linguistics, School of EECS, Peking University","Peng Cheng Laboratory, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Lab of Computational Linguistics, School of EECS, Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101441137","display_name":"Xu Sun","orcid":"https://orcid.org/0000-0001-8241-9320"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Sun","raw_affiliation_strings":["Key Lab of Computational Linguistics, School of EECS, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Lab of Computational Linguistics, School of EECS, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110285832","display_name":"Zhifang Sui","orcid":null},"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":"Zhifang Sui","raw_affiliation_strings":["Key Lab of Computational Linguistics, School of EECS, Peking University","Peng Cheng Laboratory, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Lab of Computational Linguistics, School of EECS, Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":156,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5116","last_page":"5122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9919000267982483,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.8213329911231995},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7705929279327393},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6298957467079163},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.5893928408622742},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5861164331436157},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5809339880943298},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.532001793384552},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5089731216430664},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5007264614105225},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4874913692474365},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.47400057315826416},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.46712571382522583},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4640902876853943},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4300961494445801},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06936448812484741}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8213329911231995},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7705929279327393},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6298957467079163},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.5893928408622742},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5861164331436157},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5809339880943298},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.532001793384552},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5089731216430664},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5007264614105225},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4874913692474365},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.47400057315826416},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.46712571382522583},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4640902876853943},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4300961494445801},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06936448812484741},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/711","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/711","pdf_url":"https://www.ijcai.org/proceedings/2019/0711.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/711","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/711","pdf_url":"https://www.ijcai.org/proceedings/2019/0711.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6100000143051147}],"awards":[{"id":"https://openalex.org/G138806403","display_name":null,"funder_award_id":"61876004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4918981142","display_name":null,"funder_award_id":"61751201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965033324.pdf","grobid_xml":"https://content.openalex.org/works/W2965033324.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1832693441","https://openalex.org/W2133564696","https://openalex.org/W2176263492","https://openalex.org/W2546938941","https://openalex.org/W2581637843","https://openalex.org/W2612675303","https://openalex.org/W2617566453","https://openalex.org/W2759996146","https://openalex.org/W2798931235","https://openalex.org/W2888173624","https://openalex.org/W2888556895","https://openalex.org/W2914442349","https://openalex.org/W2962824887","https://openalex.org/W2962912551","https://openalex.org/W2962944176","https://openalex.org/W2963034998","https://openalex.org/W2963126845","https://openalex.org/W2963248507","https://openalex.org/W2963541420","https://openalex.org/W2963631950","https://openalex.org/W2963667126","https://openalex.org/W2964008635","https://openalex.org/W2964222296","https://openalex.org/W2964321064","https://openalex.org/W4230563027","https://openalex.org/W4298393544"],"related_works":["https://openalex.org/W2365169615","https://openalex.org/W1970538215","https://openalex.org/W2400151637","https://openalex.org/W2975827637","https://openalex.org/W2354089692","https://openalex.org/W595497825","https://openalex.org/W4236323843","https://openalex.org/W2002616876","https://openalex.org/W3203657119","https://openalex.org/W2726367589"],"abstract_inverted_index":{"Unsupervised":[0],"text":[1,11,84],"style":[2,9,58,81,126,191],"transfer":[3,6,79],"aims":[4],"to":[5,77,123],"the":[7,30,33,39,42,46,49,55,80,83,100,103,125,135,159,183],"underlying":[8],"of":[10,82,93,102,149,185,190,203],"but":[12],"keep":[13],"its":[14],"main":[15],"content":[16,31,40,56,94,129,193],"unchanged":[17],"without":[18,90,146],"parallel":[19,150],"data.":[20,151],"Most":[21],"existing":[22],"methods":[23],"typically":[24],"follow":[25],"two":[26,113,136,176],"steps:":[27],"first":[28,50],"separating":[29],"from":[32],"original":[34],"style,":[35],"and":[36,57,95,105,112,128,195,199,206],"then":[37],"fusing":[38],"with":[41,167],"desired":[43],"style.":[44,96],"However,":[45],"separation":[47,92],"in":[48,60,63,67,188],"step":[51],"is":[52],"challenging":[53],"because":[54],"interact":[59],"subtle":[61],"ways":[62],"natural":[64],"language.":[65],"Therefore,":[66],"this":[68,133],"paper,":[69],"we":[70,98],"propose":[71],"a":[72,86,109,120,163],"dual":[73,110,121],"reinforcement":[74,144],"learning":[75,101],"framework":[76],"directly":[78],"via":[85,143],"one-step":[87,137],"mapping":[88,138],"model,":[89],"any":[91,147],"Specifically,":[97],"consider":[99],"source-to-target":[104],"target-to-source":[106],"mappings":[107],"as":[108],"task,":[111],"rewards":[114],"are":[115,209],"designed":[116],"based":[117],"on":[118,175],"such":[119],"structure":[122],"reflect":[124],"accuracy":[127],"preservation,":[130],"respectively.":[131],"In":[132],"way,":[134],"models":[139],"can":[140],"be":[141],"trained":[142],"learning,":[145],"use":[148],"Automatic":[152],"evaluations":[153,180],"show":[154],"that":[155],"our":[156,186,207],"model":[157,187,208],"outperforms":[158],"state-of-the-art":[160],"systems":[161],"by":[162],"large":[164],"margin,":[165],"especially":[166],"more":[168],"than":[169],"10":[170],"BLEU":[171],"points":[172],"improvement":[173],"averaged":[174],"benchmark":[177],"datasets.":[178],"Human":[179],"also":[181],"validate":[182],"effectiveness":[184],"terms":[189],"accuracy,":[192],"preservation":[194],"fluency.":[196],"Our":[197],"code":[198],"data,":[200],"including":[201],"outputs":[202],"all":[204],"baselines":[205],"available":[210],"at":[211],"https://github.com/luofuli/DualRL.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":26},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":51},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":10}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}