{"id":"https://openalex.org/W2806936550","doi":"https://doi.org/10.18653/v1/w18-5041","title":"Adversarial Learning of Task-Oriented Neural Dialog Models","display_name":"Adversarial Learning of Task-Oriented Neural Dialog Models","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2806936550","doi":"https://doi.org/10.18653/v1/w18-5041","mag":"2806936550"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-5041","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5041","pdf_url":"https://www.aclweb.org/anthology/W18-5041.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-5041.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100339921","display_name":"Bing Liu","orcid":"https://orcid.org/0000-0002-2365-6606"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bing Liu","raw_affiliation_strings":["Carnegie Mellon University Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University Electrical and Computer Engineering","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028182466","display_name":"Ian Lane","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Lane","raw_affiliation_strings":["Carnegie Mellon University Electrical and Computer Engineering Language Technologies Institute"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University Electrical and Computer Engineering Language Technologies Institute","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100339921"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":4.2308,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.95250862,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"350","last_page":"359"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9997000098228455,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9948999881744385,"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/dialog-box","display_name":"Dialog box","score":0.9652327299118042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8267642259597778},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7419127225875854},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7113672494888306},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6844220161437988},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6238847374916077},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5064512491226196},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5003798007965088},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.46675539016723633},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.4377080202102661},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4324834942817688},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4217790365219116},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36530590057373047},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.11807307600975037}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.9652327299118042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8267642259597778},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7419127225875854},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7113672494888306},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6844220161437988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6238847374916077},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5064512491226196},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5003798007965088},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.46675539016723633},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.4377080202102661},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4324834942817688},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4217790365219116},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36530590057373047},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.11807307600975037},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w18-5041","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5041","pdf_url":"https://www.aclweb.org/anthology/W18-5041.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-5041","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5041","pdf_url":"https://www.aclweb.org/anthology/W18-5041.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2806936550.pdf","grobid_xml":"https://content.openalex.org/works/W2806936550.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W648143168","https://openalex.org/W1522301498","https://openalex.org/W1931877416","https://openalex.org/W1932421248","https://openalex.org/W1967071444","https://openalex.org/W1975244201","https://openalex.org/W1996957559","https://openalex.org/W2061562262","https://openalex.org/W2099471712","https://openalex.org/W2119717200","https://openalex.org/W2142641780","https://openalex.org/W2151814822","https://openalex.org/W2214131199","https://openalex.org/W2251058040","https://openalex.org/W2251235149","https://openalex.org/W2412715517","https://openalex.org/W2470673105","https://openalex.org/W2581637843","https://openalex.org/W2594726847","https://openalex.org/W2601324753","https://openalex.org/W2610395436","https://openalex.org/W2749436976","https://openalex.org/W2765111838","https://openalex.org/W2949252816","https://openalex.org/W2950483141","https://openalex.org/W2951523806","https://openalex.org/W2962776342","https://openalex.org/W2962883855","https://openalex.org/W2962957031","https://openalex.org/W2963043030","https://openalex.org/W2963064439","https://openalex.org/W2963068985","https://openalex.org/W2963277051","https://openalex.org/W2963567240","https://openalex.org/W2963797754","https://openalex.org/W2964044380","https://openalex.org/W2964121744","https://openalex.org/W2964210218","https://openalex.org/W2964352131","https://openalex.org/W3104546989","https://openalex.org/W4293864724","https://openalex.org/W4295249402","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W2500779211","https://openalex.org/W48079147","https://openalex.org/W326836678","https://openalex.org/W1963944933","https://openalex.org/W2563921006","https://openalex.org/W1600043506","https://openalex.org/W2111550420","https://openalex.org/W3133451788","https://openalex.org/W2755402024","https://openalex.org/W2963043030"],"abstract_inverted_index":{"In":[0,110],"this":[1],"work,":[2],"we":[3,81,118,152],"propose":[4,82],"an":[5,83],"adversarial":[6,84,123,146],"learning":[7,14,60,85,125,148],"method":[8,86,126],"for":[9],"reward":[10,34],"estimation":[11],"in":[12,54,113,144],"reinforcement":[13],"(RL)":[15],"based":[16,25,108],"taskoriented":[17],"dialog":[18,27,58,89,93,103,124,129,147],"models.":[19],"Most":[20],"of":[21,68],"the":[22,30,102,111,121,140],"current":[23],"RL":[24,62],"task-oriented":[26],"systems":[28],"require":[29],"access":[31,158],"to":[32,70,87,100,133,159],"a":[33,65,114],"signal":[35],"from":[36,73,92],"either":[37],"user":[38,41,44,160],"feedback":[39],"or":[40,52],"ratings.":[42],"Such":[43,95],"ratings,":[45],"however,":[46],"may":[47],"not":[48],"always":[49],"be":[50],"consistent":[51],"available":[53],"practice.":[55],"Furthermore,":[56],"online":[57,145],"policy":[59,104,106],"with":[61,105,156],"typically":[63],"requires":[64],"large":[66],"number":[67],"queries":[69],"users,":[71],"suffering":[72],"sample":[74],"efficiency":[75],"problem.":[76],"To":[77],"address":[78,154],"these":[79],"challenges,":[80],"learn":[88],"rewards":[90,96],"directly":[91],"samples.":[94],"are":[97],"further":[98,138],"used":[99],"optimize":[101],"gradient":[107],"RL.":[109],"evaluation":[112],"restaurant":[115],"search":[116],"domain,":[117],"show":[119,150],"that":[120,155],"proposed":[122],"achieves":[127],"advanced":[128],"success":[130],"rate":[131],"comparing":[132],"strong":[134],"baseline":[135],"methods.":[136],"We":[137],"discuss":[139],"covariate":[141],"shift":[142],"problem":[143],"and":[149],"how":[151],"can":[153],"partial":[157],"feedback.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":8}],"updated_date":"2026-04-05T06:14:27.290980","created_date":"2025-10-10T00:00:00"}