{"id":"https://openalex.org/W2955421862","doi":"https://doi.org/10.18653/v1/w19-5901","title":"Deep Reinforcement Learning For Modeling Chit-Chat Dialog With Discrete Attributes","display_name":"Deep Reinforcement Learning For Modeling Chit-Chat Dialog With Discrete Attributes","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2955421862","doi":"https://doi.org/10.18653/v1/w19-5901","mag":"2955421862"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-5901","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5901","pdf_url":"https://www.aclweb.org/anthology/W19-5901.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 20th Annual SIGdial Meeting on Discourse and Dialogue","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/W19-5901.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039984997","display_name":"Chinnadhurai Sankar","orcid":null},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Chinnadhurai Sankar","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104067009","display_name":"Sujith Ravi","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":"Sujith Ravi","raw_affiliation_strings":["Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5039984997"],"corresponding_institution_ids":["https://openalex.org/I70931966"],"apc_list":null,"apc_paid":null,"fwci":0.868,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80760974,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"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/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/T12031","display_name":"Speech and dialogue systems","score":0.9998000264167786,"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":0.9990000128746033,"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/perplexity","display_name":"Perplexity","score":0.8897701501846313},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.8706992864608765},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8285582065582275},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8189855813980103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6030943393707275},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5791091918945312},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5380634069442749},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5272342562675476},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.14674097299575806}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.8897701501846313},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.8706992864608765},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8285582065582275},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8189855813980103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6030943393707275},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5791091918945312},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5380634069442749},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5272342562675476},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.14674097299575806},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w19-5901","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5901","pdf_url":"https://www.aclweb.org/anthology/W19-5901.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 20th Annual SIGdial Meeting on Discourse and Dialogue","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.02848","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.02848","pdf_url":"https://arxiv.org/pdf/1907.02848","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":null,"raw_type":"text"},{"id":"mag:2955421862","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1907.02848","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":"doi:10.48550/arxiv.1907.02848","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.02848","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/w19-5901","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5901","pdf_url":"https://www.aclweb.org/anthology/W19-5901.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 20th Annual SIGdial Meeting on Discourse and Dialogue","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2955421862.pdf","grobid_xml":"https://content.openalex.org/works/W2955421862.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W155915536","https://openalex.org/W192515608","https://openalex.org/W635530177","https://openalex.org/W1591706642","https://openalex.org/W1913627016","https://openalex.org/W1924770834","https://openalex.org/W2042096436","https://openalex.org/W2081802252","https://openalex.org/W2095705004","https://openalex.org/W2123442489","https://openalex.org/W2128970689","https://openalex.org/W2130942839","https://openalex.org/W2137607259","https://openalex.org/W2146785422","https://openalex.org/W2157331557","https://openalex.org/W2166637769","https://openalex.org/W2250645967","https://openalex.org/W2399880602","https://openalex.org/W2407548309","https://openalex.org/W2410983263","https://openalex.org/W2418993857","https://openalex.org/W2513380446","https://openalex.org/W2573626026","https://openalex.org/W2605133118","https://openalex.org/W2613142859","https://openalex.org/W2743945814","https://openalex.org/W2771228904","https://openalex.org/W2792376130","https://openalex.org/W2951580200","https://openalex.org/W2953113026","https://openalex.org/W2962717182","https://openalex.org/W2962852262","https://openalex.org/W2962883855","https://openalex.org/W2963206148","https://openalex.org/W2963844597","https://openalex.org/W2963958388","https://openalex.org/W2964289358","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W2980073079","https://openalex.org/W2092896632","https://openalex.org/W2970102153","https://openalex.org/W3195500343","https://openalex.org/W1555369333","https://openalex.org/W2963043030","https://openalex.org/W3088238433","https://openalex.org/W1211946649","https://openalex.org/W2034684560","https://openalex.org/W3009172038","https://openalex.org/W3074656709","https://openalex.org/W2412899141","https://openalex.org/W2831794217","https://openalex.org/W2410983263","https://openalex.org/W2040948633","https://openalex.org/W3101177506","https://openalex.org/W2808236021","https://openalex.org/W3103937890","https://openalex.org/W2919013397","https://openalex.org/W1633494854"],"abstract_inverted_index":{"Open":[0],"domain":[1],"dialog":[2,28,52,100],"systems":[3],"face":[4],"the":[5,22,36,51,79,88,91,96,104],"challenge":[6],"of":[7,90],"being":[8],"repetitive":[9],"and":[10,30,39,43,61,109,117],"producing":[11],"generic":[12],"responses.":[13,46],"In":[14],"this":[15,114],"paper,":[16],"we":[17],"demonstrate":[18,113],"that":[19],"by":[20,94],"conditioning":[21],"response":[23],"generation":[24,69],"on":[25],"interpretable":[26],"discrete":[27],"attributes":[29],"composed":[31],"attributes,":[32,101],"it":[33],"helps":[34],"improve":[35],"model":[37],"perplexity":[38],"results":[40],"in":[41],"diverse":[42],"interesting":[44],"non-redundant":[45],"We":[47,112],"propose":[48],"to":[49,66,99],"formulate":[50,78],"attribute":[53],"prediction":[54,81],"as":[55,82],"a":[56,83],"reinforcement":[57],"learning":[58],"(RL)":[59],"problem":[60],"use":[62],"policy":[63,92,105],"gradients":[64],"methods":[65],"optimize":[67],"utterance":[68],"using":[70],"long-term":[71],"rewards.":[72],"Unlike":[73],"existing":[74],"RL":[75],"approaches":[76],"which":[77],"token":[80],"policy,":[84],"our":[85],"method":[86],"reduces":[87],"complexity":[89],"optimization":[93,106],"limiting":[95],"action":[97],"space":[98],"thereby":[102],"making":[103],"more":[107],"practical":[108],"sample":[110],"efficient.":[111],"with":[115],"experimental":[116],"human":[118],"evaluations.":[119]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}