{"id":"https://openalex.org/W4385767844","doi":"https://doi.org/10.24963/ijcai.2023/561","title":"KEST: Kernel Distance Based Efficient Self-Training for Improving Controllable Text Generation","display_name":"KEST: Kernel Distance Based Efficient Self-Training for Improving Controllable Text Generation","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767844","doi":"https://doi.org/10.24963/ijcai.2023/561"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/561","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/561","pdf_url":"https://www.ijcai.org/proceedings/2023/0561.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second 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/2023/0561.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102294011","display_name":"Yuxi Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yuxi Feng","raw_affiliation_strings":["The University of British Columbia","The University of British Columbia, Vancouver, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of British Columbia","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"The University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040961637","display_name":"Xiaoyuan Yi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyuan Yi","raw_affiliation_strings":["Microsoft Research Asia","Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061340195","display_name":"Laks V. S. Lakshmanan","orcid":"https://orcid.org/0000-0002-9775-4241"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Laks V.S. Lakshmanan","raw_affiliation_strings":["The University of British Columbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044651577","display_name":"Xing Xie","orcid":"https://orcid.org/0000-0002-8608-8482"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xie","raw_affiliation_strings":["Microsoft Research Asia","Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"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":0.09570629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5049","last_page":"5057"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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":0.9812999963760376,"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":0.8037152290344238},{"id":"https://openalex.org/keywords/text-generation","display_name":"Text generation","score":0.7693572044372559},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6010331511497498},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5905137658119202},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.5590584874153137},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.5552545785903931},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5518114566802979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5001640319824219},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.49854183197021484},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4971199333667755},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44737422466278076},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3597372770309448},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2251972258090973},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.08943614363670349},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0853121280670166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8037152290344238},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.7693572044372559},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6010331511497498},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5905137658119202},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.5590584874153137},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.5552545785903931},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5518114566802979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5001640319824219},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.49854183197021484},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4971199333667755},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44737422466278076},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3597372770309448},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2251972258090973},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.08943614363670349},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0853121280670166},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/561","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/561","pdf_url":"https://www.ijcai.org/proceedings/2023/0561.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/561","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/561","pdf_url":"https://www.ijcai.org/proceedings/2023/0561.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.4399999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767844.pdf"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W2101210369","https://openalex.org/W2111316763","https://openalex.org/W2113459411","https://openalex.org/W2170240176","https://openalex.org/W2293363371","https://openalex.org/W2561274697","https://openalex.org/W2767206889","https://openalex.org/W2785896739","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2911681509","https://openalex.org/W2945260553","https://openalex.org/W2963206148","https://openalex.org/W2965373594","https://openalex.org/W2970832665","https://openalex.org/W2973049837","https://openalex.org/W2976223659","https://openalex.org/W2990019157","https://openalex.org/W2997195635","https://openalex.org/W3001197829","https://openalex.org/W3015522062","https://openalex.org/W3026041220","https://openalex.org/W3034238904","https://openalex.org/W3035160371","https://openalex.org/W3085190015","https://openalex.org/W3089635645","https://openalex.org/W3091956560","https://openalex.org/W3100355250","https://openalex.org/W3103291112","https://openalex.org/W3120044914","https://openalex.org/W3126074026","https://openalex.org/W3151450932","https://openalex.org/W3167251133","https://openalex.org/W3168921237","https://openalex.org/W3174481817","https://openalex.org/W3176618728","https://openalex.org/W3201363102","https://openalex.org/W3204846429","https://openalex.org/W4205778719","https://openalex.org/W4206636317","https://openalex.org/W4221144473","https://openalex.org/W4230085078","https://openalex.org/W4245973528","https://openalex.org/W4281806233","https://openalex.org/W4288089799","https://openalex.org/W4304731097","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2066972210","https://openalex.org/W4287812620","https://openalex.org/W3019906500","https://openalex.org/W4285816270","https://openalex.org/W2171759076","https://openalex.org/W2573463306","https://openalex.org/W1816112200","https://openalex.org/W3196937884","https://openalex.org/W67826833","https://openalex.org/W3111232506"],"abstract_inverted_index":{"Self-training":[0],"(ST)":[1],"has":[2],"come":[3],"to":[4,44,85,99],"fruition":[5],"in":[6,24,63,127],"language":[7,20,28],"understanding":[8],"tasks":[9,163],"by":[10,37,107],"producing":[11],"pseudo":[12,39,61,104,125],"labels,":[13],"which":[14,131],"reduces":[15],"the":[16,46,70,102,138],"labeling":[17],"bottleneck":[18],"of":[19,155],"model":[21],"fine-tuning.":[22],"Nevertheless,":[23],"facilitating":[25],"semi-supervised":[26],"controllable":[27,161],"generation,":[29],"ST":[30],"faces":[31],"two":[32],"key":[33],"challenges.":[34],"First,":[35],"augmented":[36],"self-generated":[38],"text,":[40],"generation":[41,57,162,177],"models":[42],"tend":[43],"over-exploit":[45],"previously":[47,139],"learned":[48],"text":[49,62,105,126,150,174],"distribution,":[50],"suffering":[51],"from":[52,101,122],"mode":[53],"collapse":[54],"and":[55,81,116,136,176],"poor":[56],"diversity.":[58],"Second,":[59],"generating":[60],"each":[64],"iteration":[65],"is":[66],"time-consuming,":[67],"severely":[68],"decelerating":[69],"training":[71],"process.":[72],"In":[73],"this":[74],"work,":[75],"we":[76],"propose":[77],"KEST,":[78],"a":[79,91,108,147,153],"novel":[80],"efficient":[82,129],"self-training":[83],"framework":[84],"handle":[86],"these":[87],"problems.":[88],"KEST":[89,119,166],"utilizes":[90],"kernel-based":[92],"loss,":[93],"rather":[94],"than":[95],"standard":[96],"cross":[97],"entropy,":[98],"learn":[100],"soft":[103],"produced":[106],"shared":[109],"non-autoregressive":[110],"generator.":[111],"We":[112],"demonstrate":[113,164],"both":[114],"theoretically":[115],"empirically":[117],"that":[118,165],"can":[120],"benefit":[121],"more":[123],"diverse":[124],"an":[128],"manner,":[130],"allows":[132],"not":[133],"only":[134],"refining":[135],"exploiting":[137],"fitted":[140],"distribution":[141],"but":[142],"also":[143],"enhanced":[144],"exploration":[145],"towards":[146],"larger":[148],"potential":[149],"space,":[151],"providing":[152],"guarantee":[154],"improved":[156],"performance.":[157],"Experiments":[158],"on":[159],"three":[160],"significantly":[167],"improves":[168],"control":[169],"accuracy":[170],"while":[171],"maintaining":[172],"comparable":[173],"fluency":[175],"diversity":[178],"against":[179],"several":[180],"strong":[181],"baselines.":[182]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}