{"id":"https://openalex.org/W4389010472","doi":"https://doi.org/10.18653/v1/2023.sigdial-1.12","title":"Dialog Action-Aware Transformer for Dialog Policy Learning","display_name":"Dialog Action-Aware Transformer for Dialog Policy Learning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389010472","doi":"https://doi.org/10.18653/v1/2023.sigdial-1.12"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.sigdial-1.12","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.sigdial-1.12","pdf_url":"https://aclanthology.org/2023.sigdial-1.12.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 24th Meeting of the Special Interest Group on Discourse and Dialogue","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.sigdial-1.12.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100411037","display_name":"Huimin Wang","orcid":"https://orcid.org/0009-0006-3932-1604"},"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":"Huimin Wang","raw_affiliation_strings":["Jarvis Lab, Tencent, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jarvis Lab, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113516068","display_name":"Wai Chung Kwan","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Wai Chung Kwan","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China","MoE Key Laboratory of High Confidence Software Technologies, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"MoE Key Laboratory of High Confidence Software Technologies, China","institution_ids":["https://openalex.org/I4210128818"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008208316","display_name":"Kam\u2010Fai Wong","orcid":"https://orcid.org/0000-0002-9427-5659"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Kam-Fai Wong","raw_affiliation_strings":["MoE Key Laboratory of High Confidence Software Technologies, China","The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of High Confidence Software Technologies, China","institution_ids":["https://openalex.org/I4210128818"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15785147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"142","last_page":"148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/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/T10181","display_name":"Natural Language Processing Techniques","score":0.9954000115394592,"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":0.975468635559082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8292929530143738},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8046941757202148},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.735906720161438},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6393222808837891},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.6232427358627319},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.556331992149353},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.49324125051498413},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.41240766644477844},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34404733777046204},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10762187838554382},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1026974618434906},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06424200534820557}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.975468635559082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8292929530143738},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8046941757202148},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.735906720161438},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6393222808837891},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.6232427358627319},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.556331992149353},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49324125051498413},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41240766644477844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34404733777046204},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10762187838554382},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1026974618434906},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06424200534820557},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.sigdial-1.12","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.sigdial-1.12","pdf_url":"https://aclanthology.org/2023.sigdial-1.12.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 24th Meeting of the Special Interest Group on Discourse and Dialogue","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.sigdial-1.12","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.sigdial-1.12","pdf_url":"https://aclanthology.org/2023.sigdial-1.12.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 24th Meeting of the Special Interest Group on Discourse and Dialogue","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4389010472.pdf"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1975244201","https://openalex.org/W2290053245","https://openalex.org/W2397581010","https://openalex.org/W2417401578","https://openalex.org/W2963341956","https://openalex.org/W2963692154","https://openalex.org/W2964006684","https://openalex.org/W2997771882","https://openalex.org/W3034330559","https://openalex.org/W3034656193","https://openalex.org/W3037879762","https://openalex.org/W3102854726","https://openalex.org/W3104546989","https://openalex.org/W3105781833","https://openalex.org/W3214586773","https://openalex.org/W4223972165","https://openalex.org/W4287870915","https://openalex.org/W4294974598","https://openalex.org/W4313703382"],"related_works":["https://openalex.org/W48079147","https://openalex.org/W2394821827","https://openalex.org/W2563921006","https://openalex.org/W1963944933","https://openalex.org/W1600043506","https://openalex.org/W2174703168","https://openalex.org/W2111550420","https://openalex.org/W2549666521","https://openalex.org/W3133893348","https://openalex.org/W2920931047"],"abstract_inverted_index":{"Recent":[0],"works":[1,23],"usually":[2],"address":[3],"Dialog":[4],"policy":[5],"learning":[6,12,62],"DPL":[7],"by":[8],"training":[9],"a":[10,28,67,75],"reinforcement":[11],"(RL)":[13],"agent":[14],"to":[15,34,43,57,84,87],"determine":[16],"the":[17,48,53,59,111,125],"best":[18],"dialog":[19,68,112],"action.":[20],"However,":[21],"existing":[22],"on":[24],"deep":[25],"RL":[26,60,101],"require":[27],"large":[29],"volume":[30],"of":[31,47,124],"agent-user":[32],"interactions":[33,105],"achieve":[35],"acceptable":[36],"performance.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41,65],"propose":[42],"make":[44],"full":[45],"use":[46],"plain":[49],"text":[50],"knowledge":[51],"from":[52],"pre-trained":[54],"language":[55],"model":[56,127],"accelerate":[58],"agent\u2019s":[61],"speed.":[63],"Specifically,":[64],"design":[66],"action-aware":[69],"transformer":[70],"encoder":[71],"(DaTrans),":[72],"which":[73],"integrates":[74],"new":[76],"fine-tuning":[77],"procedure":[78],"named":[79],"masked":[80],"last":[81],"action":[82,113],"task":[83],"encourage":[85],"DaTrans":[86,95],"be":[88],"dialog-aware":[89],"and":[90,106,122,134],"distill":[91],"action-specific":[92],"features.":[93],"Then,":[94],"is":[96],"further":[97],"optimized":[98],"in":[99,110],"an":[100],"setting":[102],"with":[103,130],"ongoing":[104],"evolves":[107],"through":[108],"exploration":[109],"space":[114],"toward":[115],"maximizing":[116],"long-term":[117],"accumulated":[118],"rewards.":[119],"The":[120],"effectiveness":[121],"efficiency":[123],"proposed":[126],"are":[128],"demonstrated":[129],"both":[131],"simulator":[132],"evaluation":[133],"human":[135],"evaluation.":[136]},"counts_by_year":[],"updated_date":"2026-01-23T23:20:30.427331","created_date":"2025-10-10T00:00:00"}