{"id":"https://openalex.org/W2774397635","doi":"https://doi.org/10.18653/v1/w17-5539","title":"Using Reinforcement Learning to Model Incrementality in a Fast-Paced Dialogue Game","display_name":"Using Reinforcement Learning to Model Incrementality in a Fast-Paced Dialogue Game","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2774397635","doi":"https://doi.org/10.18653/v1/w17-5539","mag":"2774397635"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-5539","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-5539","pdf_url":"https://www.aclweb.org/anthology/W17-5539.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 18th Annual SIGdial Meeting 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/W17-5539.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052454382","display_name":"Ramesh Manuvinakurike","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ramesh Manuvinakurike","raw_affiliation_strings":["Computer Science Department, University of Southern California","Institute for Creative Technologies, University of Southern California"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Southern California","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Institute for Creative Technologies, University of Southern California","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035399999","display_name":"David DeVault","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David DeVault","raw_affiliation_strings":["Computer Science Department, University of Southern California"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112401163","display_name":"Kallirroi Georgila","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]},{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kallirroi Georgila","raw_affiliation_strings":["Computer Science Department, University of Southern California","Institute for Creative Technologies, University of Southern California"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Southern California","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Institute for Creative Technologies, University of Southern California","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052454382"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210087747"],"apc_list":null,"apc_paid":null,"fwci":3.3259,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.93986802,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"331","last_page":"341"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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":0.9979000091552734,"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":0.8828166723251343},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.8563674688339233},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7898474931716919},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6805996298789978},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.6799350380897522},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5525720119476318},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4589667320251465},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.08566132187843323}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8828166723251343},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.8563674688339233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7898474931716919},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6805996298789978},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.6799350380897522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5525720119476318},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4589667320251465},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.08566132187843323},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w17-5539","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-5539","pdf_url":"https://www.aclweb.org/anthology/W17-5539.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 18th Annual SIGdial Meeting on Discourse and Dialogue","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-5539","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-5539","pdf_url":"https://www.aclweb.org/anthology/W17-5539.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 18th Annual SIGdial Meeting on Discourse and Dialogue","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5600000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G5259331294","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G5618972156","display_name":null,"funder_award_id":"W911NF-14-D-0005","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G8333514841","display_name":"RI: Small: Incremental Speech Processing for Rapid Dialogue","funder_award_id":"1219253","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"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2774397635.pdf","grobid_xml":"https://content.openalex.org/works/W2774397635.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W10091582","https://openalex.org/W102921666","https://openalex.org/W1010839910","https://openalex.org/W1544162381","https://openalex.org/W1598875788","https://openalex.org/W1691659217","https://openalex.org/W1974105891","https://openalex.org/W1999874108","https://openalex.org/W2045804781","https://openalex.org/W2104300420","https://openalex.org/W2106007254","https://openalex.org/W2110633879","https://openalex.org/W2150775217","https://openalex.org/W2204195844","https://openalex.org/W2246008130","https://openalex.org/W2250891614","https://openalex.org/W2251587124","https://openalex.org/W2252100656","https://openalex.org/W2278865652","https://openalex.org/W2312609093","https://openalex.org/W2399301052","https://openalex.org/W2525695389","https://openalex.org/W2586680856","https://openalex.org/W4214717370","https://openalex.org/W4246860817"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W2043093291","https://openalex.org/W2363545964"],"abstract_inverted_index":{"We":[0,21,66,95],"apply":[1],"Reinforcement":[2],"Learning":[3],"(RL)":[4],"to":[5,38,89],"the":[6,14,23,55,72,76,98,101,110,120],"problem":[7],"of":[8,16,71,93,122],"incremental":[9],"dialogue":[10,19,49],"policy":[11,24,33,53,57,74,103,112],"learning":[12],"in":[13,47,58],"context":[15],"a":[17,29,68],"fast-paced":[18],"game.":[20,50],"compare":[22],"learned":[25],"by":[26],"RL":[27,52,73,102,111],"with":[28],"high":[30],"performance":[31],"baseline":[32,56,77],"which":[34,117],"has":[35],"been":[36],"shown":[37],"perform":[39],"very":[40],"efficiently":[41],"(nearly":[42],"as":[43,45],"well":[44],"humans)":[46],"this":[48],"The":[51],"outperforms":[54],"offline":[59],"simulations":[60],"(based":[61],"on":[62],"real":[63],"user":[64],"data).":[65],"provide":[67,114],"detailed":[69],"comparison":[70],"and":[75,85,106],"policy,":[78],"including":[79],"information":[80],"about":[81],"how":[82],"much":[83],"effort":[84],"time":[86],"it":[87],"took":[88],"develop":[90],"each":[91],"one":[92],"them.":[94],"also":[96],"highlight":[97],"cases":[99],"where":[100],"performs":[104],"better,":[105],"show":[107],"that":[108],"understanding":[109],"can":[113,118],"valuable":[115],"insights":[116],"inform":[119],"creation":[121],"an":[123],"even":[124],"better":[125],"rule-based":[126],"policy.":[127]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":9},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}