{"id":"https://openalex.org/W3092995464","doi":"https://doi.org/10.18653/v1/2020.emnlp-main.327","title":"Human-centric dialog training via offline reinforcement learning","display_name":"Human-centric dialog training via offline reinforcement learning","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3092995464","doi":"https://doi.org/10.18653/v1/2020.emnlp-main.327","mag":"3092995464"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.emnlp-main.327","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.emnlp-main.327","pdf_url":"https://www.aclweb.org/anthology/2020.emnlp-main.327.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 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/2020.emnlp-main.327.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046953322","display_name":"Natasha Jaques","orcid":"https://orcid.org/0000-0002-8413-9469"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Natasha Jaques","raw_affiliation_strings":["Equal contribution","Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Equal contribution","institution_ids":[]},{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020734965","display_name":"Judy Hanwen Shen","orcid":"https://orcid.org/0000-0002-7864-5242"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Judy Hanwen Shen","raw_affiliation_strings":["Equal contribution","Massachusetts Institute of Technology, Cambridge, USA","Stanford University, Stanford, United States"],"affiliations":[{"raw_affiliation_string":"Equal contribution","institution_ids":[]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Stanford University, Stanford, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022368228","display_name":"Asma Ghandeharioun","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Asma Ghandeharioun","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, USA","Massachusetts Institute of Technology, Cambridge, United States"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070225432","display_name":"Craig Ferguson","orcid":"https://orcid.org/0000-0003-0053-024X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Craig Ferguson","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, USA","Massachusetts Institute of Technology, Cambridge, United States"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065661266","display_name":"\u00c0gata Lapedriza","orcid":"https://orcid.org/0000-0002-5248-0443"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"id":"https://openalex.org/I138847295","display_name":"Universitat Oberta de Catalunya","ror":"https://ror.org/01f5wp925","country_code":"ES","type":"education","lineage":["https://openalex.org/I138847295"]}],"countries":["ES","US"],"is_corresponding":false,"raw_author_name":"Agata Lapedriza","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, USA","Universitat Oberta de Catalunya, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Universitat Oberta de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I138847295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104351492","display_name":"N. S. Jones","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Noah Jones","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, USA","Massachusetts Institute of Technology, Cambridge, United States"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061613634","display_name":"Shixiang Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shixiang Gu","raw_affiliation_strings":["Google Research, Mountain View, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087366916","display_name":"Rosalind W. Picard","orcid":"https://orcid.org/0000-0002-5661-0022"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rosalind Picard","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, USA","Massachusetts Institute of Technology, Cambridge, United States"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5046953322"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.0971,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.83021621,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3985","last_page":"4003"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T12031","display_name":"Speech and dialogue systems","score":0.9993000030517578,"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":0.9955000281333923,"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":0.8558933734893799},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8068336248397827},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.760651171207428},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6636210680007935},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5718445777893066},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4748687446117401},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4735250473022461},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44884029030799866},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4480293095111847},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4225195348262787},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32553207874298096}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8558933734893799},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8068336248397827},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.760651171207428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6636210680007935},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5718445777893066},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4748687446117401},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4735250473022461},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44884029030799866},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4480293095111847},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4225195348262787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32553207874298096},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.18653/v1/2020.emnlp-main.327","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.emnlp-main.327","pdf_url":"https://www.aclweb.org/anthology/2020.emnlp-main.327.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 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.05848","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.05848","pdf_url":"https://arxiv.org/pdf/2010.05848","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},{"id":"mag:3092995464","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2010.05848","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"pmh:oai:dspace.mit.edu:1721.1/146608","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/146608","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Association for Computational Linguistics","raw_type":"http://purl.org/eprint/type/ConferencePaper"},{"id":"doi:10.48550/arxiv.2010.05848","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.05848","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/2020.emnlp-main.327","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.emnlp-main.327","pdf_url":"https://www.aclweb.org/anthology/2020.emnlp-main.327.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 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4699999988079071}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334473","display_name":"Quest for Intelligence, Massachusetts Institute of Technology","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3092995464.pdf","grobid_xml":"https://content.openalex.org/works/W3092995464.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1499669280","https://openalex.org/W1514587017","https://openalex.org/W1522301498","https://openalex.org/W1757796397","https://openalex.org/W1821462560","https://openalex.org/W2010771450","https://openalex.org/W2035934535","https://openalex.org/W2042585112","https://openalex.org/W2058010765","https://openalex.org/W2095545872","https://openalex.org/W2107662876","https://openalex.org/W2125320996","https://openalex.org/W2126601124","https://openalex.org/W2130801532","https://openalex.org/W2145060720","https://openalex.org/W2152329275","https://openalex.org/W2264742718","https://openalex.org/W2410983263","https://openalex.org/W2410985346","https://openalex.org/W2465828773","https://openalex.org/W2559038528","https://openalex.org/W2751124354","https://openalex.org/W2755402024","https://openalex.org/W2781726626","https://openalex.org/W2785738552","https://openalex.org/W2794557536","https://openalex.org/W2798689729","https://openalex.org/W2806600904","https://openalex.org/W2906579211","https://openalex.org/W2910458567","https://openalex.org/W2913350542","https://openalex.org/W2936304709","https://openalex.org/W2947150733","https://openalex.org/W2949561945","https://openalex.org/W2949608212","https://openalex.org/W2949918260","https://openalex.org/W2950593761","https://openalex.org/W2951000191","https://openalex.org/W2951520714","https://openalex.org/W2952594289","https://openalex.org/W2953334758","https://openalex.org/W2962883855","https://openalex.org/W2963567240","https://openalex.org/W2963879591","https://openalex.org/W2963918774","https://openalex.org/W2964044380","https://openalex.org/W2964059111","https://openalex.org/W2971262355","https://openalex.org/W2973379954","https://openalex.org/W2973940173","https://openalex.org/W3000779003","https://openalex.org/W3036394672","https://openalex.org/W3106003309"],"related_works":["https://openalex.org/W3102788578","https://openalex.org/W3212887262","https://openalex.org/W3183467098","https://openalex.org/W3096964654","https://openalex.org/W2973940173","https://openalex.org/W3178748050","https://openalex.org/W3167658443","https://openalex.org/W3210216754","https://openalex.org/W2990162188","https://openalex.org/W52170320","https://openalex.org/W3112266718","https://openalex.org/W2984869362","https://openalex.org/W3103610908","https://openalex.org/W3111500217","https://openalex.org/W3103763075","https://openalex.org/W3101483449","https://openalex.org/W3168250321","https://openalex.org/W2998219625","https://openalex.org/W2891470378","https://openalex.org/W3202454639"],"abstract_inverted_index":{"Natasha":[0],"Jaques,":[1],"Judy":[2],"Hanwen":[3],"Shen,":[4],"Asma":[5],"Ghandeharioun,":[6],"Craig":[7],"Ferguson,":[8],"Agata":[9],"Lapedriza,":[10],"Noah":[11],"Jones,":[12],"Shixiang":[13],"Gu,":[14],"Rosalind":[15],"Picard.":[16],"Proceedings":[17],"of":[18],"the":[19],"2020":[20],"Conference":[21],"on":[22],"Empirical":[23],"Methods":[24],"in":[25],"Natural":[26],"Language":[27],"Processing":[28],"(EMNLP).":[29],"2020.":[30]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}