{"id":"https://openalex.org/W2970028737","doi":"https://doi.org/10.18653/v1/d19-1010","title":"Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialog","display_name":"Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialog","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2970028737","doi":"https://doi.org/10.18653/v1/d19-1010","mag":"2970028737"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d19-1010","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-1010","pdf_url":"https://www.aclweb.org/anthology/D19-1010.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 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D19-1010.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016443523","display_name":"Ryuichi Takanobu","orcid":"https://orcid.org/0000-0002-1382-8275"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ryuichi Takanobu","raw_affiliation_strings":["DCST,","Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DCST,","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102021630","display_name":"Hanlin Zhu","orcid":"https://orcid.org/0000-0002-8954-3479"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanlin Zhu","raw_affiliation_strings":["IIIS, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIS, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044042138","display_name":"Minlie Huang","orcid":"https://orcid.org/0000-0001-7111-1849"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minlie Huang","raw_affiliation_strings":["DCST,","Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DCST,","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"100","last_page":"110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T12031","display_name":"Speech and dialogue systems","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/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/T12128","display_name":"AI in Service Interactions","score":0.9943000078201294,"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":0.9742850065231323},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7951425313949585},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7490782141685486},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7138544917106628},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.5919531583786011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5830450057983398},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.530897319316864},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5000123977661133},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.487781822681427},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4457722008228302},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.4434114098548889},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3994336724281311},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.11048075556755066},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07900857925415039}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.9742850065231323},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7951425313949585},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7490782141685486},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7138544917106628},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.5919531583786011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5830450057983398},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.530897319316864},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5000123977661133},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.487781822681427},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4457722008228302},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4434114098548889},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3994336724281311},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.11048075556755066},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07900857925415039},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/d19-1010","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-1010","pdf_url":"https://www.aclweb.org/anthology/D19-1010.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 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1908.10719","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.10719","pdf_url":"https://arxiv.org/pdf/1908.10719","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2970028737","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1908.10719","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1908.10719","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1908.10719","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/d19-1010","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-1010","pdf_url":"https://www.aclweb.org/anthology/D19-1010.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 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G6153920497","display_name":null,"funder_award_id":"61876096","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7155907028","display_name":null,"funder_award_id":"61936010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2970028737.pdf","grobid_xml":"https://content.openalex.org/works/W2970028737.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W744662145","https://openalex.org/W2007221309","https://openalex.org/W2022398498","https://openalex.org/W2062175565","https://openalex.org/W2098774185","https://openalex.org/W2128970689","https://openalex.org/W2147544021","https://openalex.org/W2177156214","https://openalex.org/W2468710617","https://openalex.org/W2558661633","https://openalex.org/W2566467060","https://openalex.org/W2736601468","https://openalex.org/W2739748921","https://openalex.org/W2759104452","https://openalex.org/W2798914047","https://openalex.org/W2806600904","https://openalex.org/W2806936550","https://openalex.org/W2889186204","https://openalex.org/W2899908862","https://openalex.org/W2939790162","https://openalex.org/W2950483141","https://openalex.org/W2962776342","https://openalex.org/W2962879001","https://openalex.org/W2963064439","https://openalex.org/W2963068985","https://openalex.org/W2963095800","https://openalex.org/W2963170138","https://openalex.org/W2963277051","https://openalex.org/W2963306198","https://openalex.org/W2963508354","https://openalex.org/W2963993502","https://openalex.org/W2964104642","https://openalex.org/W3104546989"],"related_works":["https://openalex.org/W2970828515","https://openalex.org/W2736601468","https://openalex.org/W2963341956","https://openalex.org/W2145339207","https://openalex.org/W2062175565","https://openalex.org/W2962996309","https://openalex.org/W2963068985","https://openalex.org/W2891732163","https://openalex.org/W2412899141","https://openalex.org/W2806936550","https://openalex.org/W2810840719","https://openalex.org/W2798494119","https://openalex.org/W1975244201","https://openalex.org/W2964018203","https://openalex.org/W3015216216","https://openalex.org/W2805406810","https://openalex.org/W2571927164","https://openalex.org/W2774104751","https://openalex.org/W2022398498","https://openalex.org/W3175400354"],"abstract_inverted_index":{"Ryuichi":[0],"Takanobu,":[1],"Hanlin":[2],"Zhu,":[3],"Minlie":[4],"Huang.":[5],"Proceedings":[6],"of":[7],"the":[8,19],"2019":[9],"Conference":[10,23],"on":[11,24],"Empirical":[12],"Methods":[13],"in":[14],"Natural":[15,25],"Language":[16,26],"Processing":[17,27],"and":[18],"9th":[20],"International":[21],"Joint":[22],"(EMNLP-IJCNLP).":[28],"2019.":[29]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}