{"id":"https://openalex.org/W2962776342","doi":"https://doi.org/10.18653/v1/w16-3601","title":"Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning","display_name":"Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2962776342","doi":"https://doi.org/10.18653/v1/w16-3601","mag":"2962776342"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w16-3601","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-3601","pdf_url":"https://www.aclweb.org/anthology/W16-3601.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 17th Annual Meeting of the Special Interest Group\n          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/W16-3601.pdf","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"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5114246802"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":37.9891,"has_fulltext":true,"cited_by_count":190,"citation_normalized_percentile":{"value":0.99735892,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9973999857902527,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8589679598808289},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.840961754322052},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.8249783515930176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6451271176338196},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5832288265228271},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.493745893239975},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4390503466129303},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43147727847099304},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4136064648628235}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8589679598808289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.840961754322052},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.8249783515930176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6451271176338196},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5832288265228271},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.493745893239975},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4390503466129303},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43147727847099304},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4136064648628235},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w16-3601","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-3601","pdf_url":"https://www.aclweb.org/anthology/W16-3601.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 17th Annual Meeting of the Special Interest Group\n          on Discourse and Dialogue","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w16-3601","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-3601","pdf_url":"https://www.aclweb.org/anthology/W16-3601.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 17th Annual Meeting of the Special Interest Group\n          on Discourse and Dialogue","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7328387495","display_name":"CI-NEW: Collaborative Research: DialPort: Enabling Spoken Dialog Research with Real Data","funder_award_id":"1512973","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2962776342.pdf","grobid_xml":"https://content.openalex.org/works/W2962776342.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W178897730","https://openalex.org/W1491843047","https://openalex.org/W1515851193","https://openalex.org/W1524766440","https://openalex.org/W1573558308","https://openalex.org/W1582147469","https://openalex.org/W1591706642","https://openalex.org/W1681299129","https://openalex.org/W1777239053","https://openalex.org/W1778387566","https://openalex.org/W1934909785","https://openalex.org/W2022398498","https://openalex.org/W2064675550","https://openalex.org/W2088923570","https://openalex.org/W2094728533","https://openalex.org/W2119015791","https://openalex.org/W2121092017","https://openalex.org/W2123651102","https://openalex.org/W2130942839","https://openalex.org/W2145339207","https://openalex.org/W2170323078","https://openalex.org/W2201581102","https://openalex.org/W2231198303","https://openalex.org/W2250297846","https://openalex.org/W2251235149","https://openalex.org/W2251273220","https://openalex.org/W2438667436","https://openalex.org/W2746553466","https://openalex.org/W2962883855","https://openalex.org/W2962938178","https://openalex.org/W2963797754","https://openalex.org/W2963963856","https://openalex.org/W3116006368"],"related_works":["https://openalex.org/W2098987383","https://openalex.org/W2417260800","https://openalex.org/W2795961259","https://openalex.org/W1596203174","https://openalex.org/W2117933979","https://openalex.org/W4298396513","https://openalex.org/W2283130723","https://openalex.org/W103938586","https://openalex.org/W2104718772","https://openalex.org/W4233992201"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"end-to-end":[4],"framework":[5],"for":[6,32],"task-oriented":[7],"dialog":[8,37,91],"systems":[9],"using":[10],"a":[11,25,42,66,85],"variant":[12],"of":[13,49,88],"Deep":[14],"Recurrent":[15],"Q-Networks":[16],"(DRQN).":[17],"The":[18],"model":[19,64],"is":[20],"able":[21],"to":[22,55],"interface":[23],"with":[24],"relational":[26],"database":[27],"and":[28,36,52,83],"jointly":[29],"learn":[30],"policies":[31],"both":[33],"language":[34],"understanding":[35],"strategy.":[38],"Moreover,":[39],"we":[40],"propose":[41],"hybrid":[43],"algorithm":[44],"that":[45,75],"combines":[46],"the":[47,62,76,80,89],"strength":[48],"reinforcement":[50],"learning":[51,54,58],"supervised":[53],"achieve":[56],"faster":[57],"speed.":[59],"We":[60],"evaluated":[61],"proposed":[63,77],"on":[65],"20":[67],"Question":[68],"Game":[69],"conversational":[70],"game":[71],"simulator.":[72],"Results":[73],"show":[74],"method":[78],"outperforms":[79],"modular-based":[81],"baseline":[82],"learns":[84],"distributed":[86],"representation":[87],"latent":[90],"state.":[92]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":38},{"year":2019,"cited_by_count":34},{"year":2018,"cited_by_count":34},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-22T08:38:42.863108","created_date":"2025-10-10T00:00:00"}