{"id":"https://openalex.org/W2915295540","doi":"https://doi.org/10.18653/v1/n19-1123","title":"Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models","display_name":"Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2915295540","doi":"https://doi.org/10.18653/v1/n19-1123","mag":"2915295540"},"language":"en","primary_location":{"id":"doi:10.18653/v1/n19-1123","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n19-1123","pdf_url":null,"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 2019 Conference of the North","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/n19-1123","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114246802","display_name":"Tiancheng Zhao","orcid":"https://orcid.org/0000-0002-7443-0666"},"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":"Tiancheng Zhao","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032594507","display_name":"Kaige Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaige Xie","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077285164","display_name":"Maxine Esk\u00e9nazi","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":"Maxine Eskenazi","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5114246802"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":14.7483,"has_fulltext":false,"cited_by_count":125,"citation_normalized_percentile":{"value":0.99133864,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1208","last_page":"1218"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987000226974487,"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/T12031","display_name":"Speech and dialogue systems","score":0.9987000226974487,"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":0.8452940583229065},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.6317349672317505},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6198832392692566},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6099233627319336},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5799216032028198},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5606057643890381},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47144851088523865},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.4652899503707886},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.4444599747657776},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.4421161413192749},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4219355881214142},{"id":"https://openalex.org/keywords/latent-variable-model","display_name":"Latent variable model","score":0.4113406240940094},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40055516362190247},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.37852123379707336},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.19734865427017212},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.17591184377670288},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.13163360953330994},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12661045789718628}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.8452940583229065},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.6317349672317505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6198832392692566},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6099233627319336},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5799216032028198},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5606057643890381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47144851088523865},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.4652899503707886},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.4444599747657776},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.4421161413192749},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4219355881214142},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.4113406240940094},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40055516362190247},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.37852123379707336},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.19734865427017212},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.17591184377670288},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.13163360953330994},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12661045789718628},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/n19-1123","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n19-1123","pdf_url":null,"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 2019 Conference of the North","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/n19-1123","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n19-1123","pdf_url":null,"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 2019 Conference of the North","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W178897730","https://openalex.org/W1518951372","https://openalex.org/W1591706642","https://openalex.org/W1902237438","https://openalex.org/W1959608418","https://openalex.org/W1975244201","https://openalex.org/W2023384780","https://openalex.org/W2047335008","https://openalex.org/W2107726111","https://openalex.org/W2108682071","https://openalex.org/W2116009284","https://openalex.org/W2119717200","https://openalex.org/W2119850747","https://openalex.org/W2129405869","https://openalex.org/W2157331557","https://openalex.org/W2170323078","https://openalex.org/W2250297846","https://openalex.org/W2251149342","https://openalex.org/W2412715517","https://openalex.org/W2438667436","https://openalex.org/W2470673105","https://openalex.org/W2547875792","https://openalex.org/W2593696076","https://openalex.org/W2594726847","https://openalex.org/W2602275733","https://openalex.org/W2603266952","https://openalex.org/W2749436976","https://openalex.org/W2751124354","https://openalex.org/W2780155557","https://openalex.org/W2962717182","https://openalex.org/W2962776342","https://openalex.org/W2962852262","https://openalex.org/W2962879001","https://openalex.org/W2962883855","https://openalex.org/W2963068985","https://openalex.org/W2963134326","https://openalex.org/W2963167310","https://openalex.org/W2963170138","https://openalex.org/W2963411289","https://openalex.org/W2963641152","https://openalex.org/W2963790827","https://openalex.org/W2963797754","https://openalex.org/W2963881016","https://openalex.org/W2964006684","https://openalex.org/W2964044380","https://openalex.org/W3022187094","https://openalex.org/W3099293669"],"related_works":["https://openalex.org/W2461917396","https://openalex.org/W1966667550","https://openalex.org/W2037497866","https://openalex.org/W4243467573","https://openalex.org/W1502435251","https://openalex.org/W62001224","https://openalex.org/W3032390039","https://openalex.org/W1584341211","https://openalex.org/W3122667150","https://openalex.org/W3145681568"],"abstract_inverted_index":{"Tiancheng":[0],"Zhao,":[1],"Kaige":[2],"Xie,":[3],"Maxine":[4],"Eskenazi.":[5],"Proceedings":[6],"of":[7,11,16],"the":[8,12,17],"2019":[9],"Conference":[10],"North":[13],"American":[14],"Chapter":[15],"Association":[18],"for":[19],"Computational":[20],"Linguistics:":[21],"Human":[22],"Language":[23],"Technologies,":[24],"Volume":[25],"1":[26],"(Long":[27],"and":[28],"Short":[29],"Papers).":[30],"2019.":[31]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":29},{"year":2020,"cited_by_count":45},{"year":2019,"cited_by_count":10}],"updated_date":"2026-06-10T14:10:52.464848","created_date":"2025-10-10T00:00:00"}
