{"id":"https://openalex.org/W3208178363","doi":"https://doi.org/10.1145/3459637.3482333","title":"Corrective Guidance and Learning for Dialogue Management","display_name":"Corrective Guidance and Learning for Dialogue Management","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3208178363","doi":"https://doi.org/10.1145/3459637.3482333","mag":"3208178363"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3482333","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information &amp; Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5043243811","display_name":"Mahdin Rohmatillah","orcid":"https://orcid.org/0000-0001-8417-2165"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Mahdin Rohmatillah","raw_affiliation_strings":["National Yang Ming Chiao Tung University, Hsinchu, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan Roc","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["National Yang Ming Chiao Tung University, Hsinchu, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan Roc","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1548","last_page":"1557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994000196456909,"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":0.9829000234603882,"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/computer-science","display_name":"Computer science","score":0.80381178855896},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7990683317184448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6317418813705444},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5145370364189148},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4581346809864044},{"id":"https://openalex.org/keywords/corrective-feedback","display_name":"Corrective feedback","score":0.42295822501182556},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41875842213630676},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1068510115146637}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.80381178855896},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7990683317184448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6317418813705444},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5145370364189148},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4581346809864044},{"id":"https://openalex.org/C2779305910","wikidata":"https://www.wikidata.org/wiki/Q5172809","display_name":"Corrective feedback","level":2,"score":0.42295822501182556},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41875842213630676},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1068510115146637},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3459637.3482333","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information &amp; Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2718465553","display_name":null,"funder_award_id":"MOST 110-2221-E-A49-073-MY3","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2056985955","https://openalex.org/W2144920344","https://openalex.org/W2156517809","https://openalex.org/W2169203263","https://openalex.org/W2242047860","https://openalex.org/W2405331948","https://openalex.org/W2739936944","https://openalex.org/W2766329790","https://openalex.org/W2798494119","https://openalex.org/W2889186204","https://openalex.org/W2889448364","https://openalex.org/W2896457183","https://openalex.org/W2951091467","https://openalex.org/W2962957031","https://openalex.org/W2963184621","https://openalex.org/W2963412005","https://openalex.org/W2963433587","https://openalex.org/W2963508354","https://openalex.org/W2964006684","https://openalex.org/W2964121744","https://openalex.org/W2964411643","https://openalex.org/W2970828515","https://openalex.org/W2971737394","https://openalex.org/W2973112754","https://openalex.org/W2985067290","https://openalex.org/W2985237994","https://openalex.org/W2997771882","https://openalex.org/W2998458199","https://openalex.org/W3034782127","https://openalex.org/W3037879762","https://openalex.org/W3088273075","https://openalex.org/W3095200696","https://openalex.org/W3105184920","https://openalex.org/W3111496951","https://openalex.org/W3117383065","https://openalex.org/W3132647335","https://openalex.org/W3197004354","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4390193239","https://openalex.org/W4213266652","https://openalex.org/W2899872056","https://openalex.org/W3164368351","https://openalex.org/W2998735842","https://openalex.org/W4386265809","https://openalex.org/W3133706844","https://openalex.org/W2893467525","https://openalex.org/W3007191706","https://openalex.org/W2791575529"],"abstract_inverted_index":{"Establishing":[0],"robust":[1,98],"dialogue":[2,14,80,200],"policy":[3,33,123],"with":[4,82,89],"low":[5],"computation":[6],"cost":[7],"is":[8,46,75,93,114,129,148],"challenging,":[9],"especially":[10],"for":[11],"multi-domain":[12,79],"task-oriented":[13],"management":[15,81],"due":[16],"to":[17,77,95,131,150,173],"the":[18,31,58,86,103,111,121,133,146,162,174,180,196],"high":[19],"complexity":[20],"in":[21,107,152,199],"state":[22],"and":[23],"action":[24],"spaces.":[25],"The":[26,155],"previous":[27],"works":[28],"mostly":[29],"using":[30,117],"deterministic":[32],"optimization":[34],"only":[35],"attain":[36],"moderate":[37],"performance.":[38],"Meanwhile,":[39],"state-of-the-art":[40,167],"result":[41,168],"that":[42,145,161,192],"uses":[43,193],"end-to-end":[44,158],"approach":[45],"computationally":[47],"demanding":[48],"since":[49],"it":[50],"utilizes":[51],"a":[52,66,97],"large-scaled":[53],"language":[54],"model":[55,100,113,198],"based":[56],"on":[57,157],"generative":[59],"pre-trained":[60,99,112],"transformer-2":[61],"(GPT-2).":[62],"In":[63],"this":[64],"study,":[65],"new":[67],"learning":[68,73,119,127,164],"procedure":[69],"consisting":[70],"of":[71,183],"three":[72],"stages":[74],"presented":[76],"improve":[78],"corrective":[83,139],"guidance.":[84],"Firstly,":[85],"behavior":[87],"cloning":[88],"an":[90],"auxiliary":[91],"task":[92],"developed":[94],"build":[96],"by":[101,116,136,169],"mitigating":[102],"causal":[104],"confusion":[105],"problem":[106],"imitation":[108],"learning.":[109],"Next,":[110],"rectified":[115],"reinforcement":[118],"via":[120],"proximal":[122],"optimization.":[124],"Lastly,":[125],"human-in-the-loop":[126],"strategy":[128],"fulfilled":[130],"enhance":[132],"agent":[134,143,147],"performance":[135],"directly":[137],"providing":[138],"feedback":[140],"from":[141],"rule-based":[142,175],"so":[144],"prevented":[149],"trap":[151],"confounded":[153],"states.":[154],"experiments":[156],"evaluation":[159],"show":[160],"proposed":[163],"method":[165,178],"achieves":[166],"performing":[170],"nearly":[171],"identical":[172],"agent.":[176],"This":[177],"outperforms":[179],"second":[181],"place":[182],"9th":[184],"dialog":[185],"system":[186],"technology":[187],"challenge":[188],"(DSTC9)":[189],"track":[190],"2":[191],"GPT-2":[194],"as":[195],"core":[197],"management.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
