{"id":"https://openalex.org/W2057244568","doi":"https://doi.org/10.1162/coli_a_00038","title":"Learning and Evaluation of Dialogue Strategies for New Applications: Empirical Methods for Optimization from Small Data Sets","display_name":"Learning and Evaluation of Dialogue Strategies for New Applications: Empirical Methods for Optimization from Small Data Sets","publication_year":2011,"publication_date":"2011-01-21","ids":{"openalex":"https://openalex.org/W2057244568","doi":"https://doi.org/10.1162/coli_a_00038","mag":"2057244568"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00038","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00038","pdf_url":"https://direct.mit.edu/coli/article-pdf/37/1/153/1810303/coli_a_00038.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://direct.mit.edu/coli/article-pdf/37/1/153/1810303/coli_a_00038.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076593865","display_name":"Verena Rieser","orcid":"https://orcid.org/0000-0001-6117-4395"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Verena Rieser","raw_affiliation_strings":["School of GeoSciences/University of Edinburgh","School of GeoSciences, University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of GeoSciences/University of Edinburgh","institution_ids":[]},{"raw_affiliation_string":"School of GeoSciences, University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010949145","display_name":"Oliver Lemon","orcid":"https://orcid.org/0000-0001-9497-4743"},"institutions":[{"id":"https://openalex.org/I32062511","display_name":"Heriot-Watt University","ror":"https://ror.org/04mghma93","country_code":"GB","type":"education","lineage":["https://openalex.org/I32062511"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oliver Lemon","raw_affiliation_strings":["School of Mathematical and Computer Sciences/Heriot-Watt University","School of Mathematical and Computer Sciences. Heriot-Watt University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical and Computer Sciences/Heriot-Watt University","institution_ids":[]},{"raw_affiliation_string":"School of Mathematical and Computer Sciences. Heriot-Watt University","institution_ids":["https://openalex.org/I32062511"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.1962,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.974245,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"37","issue":"1","first_page":"153","last_page":"196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":1.0,"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":1.0,"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":0.9977999925613403,"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":0.9965000152587891,"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":0.8540492653846741},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7831270694732666},{"id":"https://openalex.org/keywords/wizard","display_name":"Wizard","score":0.623656690120697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5719361305236816},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5067475438117981},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5052719712257385},{"id":"https://openalex.org/keywords/wizard-of-oz","display_name":"Wizard of oz","score":0.49953770637512207},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4958721101284027},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42905017733573914},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.2120729386806488}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8540492653846741},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7831270694732666},{"id":"https://openalex.org/C2776784076","wikidata":"https://www.wikidata.org/wiki/Q580334","display_name":"Wizard","level":2,"score":0.623656690120697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5719361305236816},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5067475438117981},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5052719712257385},{"id":"https://openalex.org/C2987423310","wikidata":"https://www.wikidata.org/wiki/Q18159725","display_name":"Wizard of oz","level":2,"score":0.49953770637512207},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4958721101284027},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42905017733573914},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2120729386806488},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/coli_a_00038","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00038","pdf_url":"https://direct.mit.edu/coli/article-pdf/37/1/153/1810303/coli_a_00038.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7a9b681b753f40bf8b42e5017f6f019f","is_oa":false,"landing_page_url":"https://doaj.org/article/7a9b681b753f40bf8b42e5017f6f019f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 37, Iss 1 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00038","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00038","pdf_url":"https://direct.mit.edu/coli/article-pdf/37/1/153/1810303/coli_a_00038.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4608247269","display_name":null,"funder_award_id":"EP/G069840/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":85,"referenced_works":["https://openalex.org/W1375381","https://openalex.org/W18698765","https://openalex.org/W51847911","https://openalex.org/W62710299","https://openalex.org/W85739093","https://openalex.org/W91852349","https://openalex.org/W119047706","https://openalex.org/W119177792","https://openalex.org/W120790241","https://openalex.org/W148267512","https://openalex.org/W154525918","https://openalex.org/W160067033","https://openalex.org/W173870384","https://openalex.org/W182831726","https://openalex.org/W224047168","https://openalex.org/W268459713","https://openalex.org/W276707516","https://openalex.org/W605575788","https://openalex.org/W1486212465","https://openalex.org/W1544729927","https://openalex.org/W1560107318","https://openalex.org/W1570448133","https://openalex.org/W1579838312","https://openalex.org/W1653632886","https://openalex.org/W1670263352","https://openalex.org/W1681299129","https://openalex.org/W1695997110","https://openalex.org/W1757949796","https://openalex.org/W1762122460","https://openalex.org/W1969733117","https://openalex.org/W1974821254","https://openalex.org/W1980340273","https://openalex.org/W1986199072","https://openalex.org/W1987725259","https://openalex.org/W2009814304","https://openalex.org/W2021151961","https://openalex.org/W2040948633","https://openalex.org/W2049633694","https://openalex.org/W2052752543","https://openalex.org/W2056561350","https://openalex.org/W2062175565","https://openalex.org/W2062244797","https://openalex.org/W2063241222","https://openalex.org/W2064094392","https://openalex.org/W2066986772","https://openalex.org/W2067694790","https://openalex.org/W2080887205","https://openalex.org/W2089234697","https://openalex.org/W2095977914","https://openalex.org/W2101445408","https://openalex.org/W2105303215","https://openalex.org/W2106482783","https://openalex.org/W2106547558","https://openalex.org/W2109730238","https://openalex.org/W2111273940","https://openalex.org/W2113786274","https://openalex.org/W2115101920","https://openalex.org/W2118030876","https://openalex.org/W2121528300","https://openalex.org/W2125055259","https://openalex.org/W2126810476","https://openalex.org/W2128965063","https://openalex.org/W2132997613","https://openalex.org/W2134040603","https://openalex.org/W2134466368","https://openalex.org/W2136449704","https://openalex.org/W2141839844","https://openalex.org/W2149029524","https://openalex.org/W2155898337","https://openalex.org/W2157134106","https://openalex.org/W2158587394","https://openalex.org/W2159250980","https://openalex.org/W2160219061","https://openalex.org/W2168490009","https://openalex.org/W2174559414","https://openalex.org/W2226536778","https://openalex.org/W2438667436","https://openalex.org/W2603612888","https://openalex.org/W2624335110","https://openalex.org/W2788204336","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W2966207845","https://openalex.org/W3006034187","https://openalex.org/W3099293669"],"related_works":["https://openalex.org/W4246078203","https://openalex.org/W659328528","https://openalex.org/W2127135847","https://openalex.org/W1550648368","https://openalex.org/W603474643","https://openalex.org/W2152818631","https://openalex.org/W1545061903","https://openalex.org/W1504394863","https://openalex.org/W2757160751","https://openalex.org/W3204363446"],"abstract_inverted_index":{"We":[0,63,185],"present":[1,121],"a":[2,40,76],"new":[3],"data-driven":[4,41,95,208],"methodology":[5],"for":[6,100],"simulation-based":[7,109,130],"dialogue":[8,25,29,71],"strategy":[9,138],"learning,":[10],"which":[11,79,117],"allows":[12,94,111],"us":[13,112],"to":[14,68,113,195],"address":[15],"several":[16],"problems":[17],"in":[18,122,161],"the":[19,48,123,134,142,178,204,207],"field":[20],"of":[21,24,85,91,97,206],"automatic":[22],"optimization":[23],"strategies:":[26],"learning":[27],"effective":[28],"strategies":[30,72,99],"when":[31,159,169],"no":[32,103],"initial":[33],"data":[34,93,143],"or":[35],"system":[36],"exists,":[37],"and":[38,53,60,163,200],"determining":[39],"reward":[42,158,168,209],"function.":[43,210],"In":[44],"addition,":[45],"we":[46,201],"evaluate":[47,203],"result":[49],"with":[50,75,171,197],"real":[51,61,172,198],"users,":[52,199],"explore":[54],"how":[55],"results":[56,127,189],"transfer":[57,194],"between":[58],"simulated":[59,77,191],"interactions.":[62],"use":[64,90],"Reinforcement":[65],"Learning":[66],"(RL)":[67],"learn":[69],"multimodal":[70],"by":[73,144],"interaction":[74,192,196],"environment":[78],"is":[80,106],"\u201cbootstrapped\u201d":[81],"from":[82,141,190],"small":[83],"amounts":[84],"Wizard-of-Oz":[86],"(WOZ)":[87],"data.":[88,125],"This":[89],"WOZ":[92],"development":[96],"optimal":[98,115],"domains":[101],"where":[102],"working":[104],"prototype":[105],"available.":[107],"Using":[108],"RL":[110,131],"find":[114],"policies":[116],"are":[118],"not":[119],"(necessarily)":[120],"original":[124],"Our":[126],"show":[128,187],"that":[129,188],"significantly":[132],"outperforms":[133],"average":[135,154,182],"(human":[136],"wizard)":[137],"as":[139],"learned":[140],"using":[145],"Supervised":[146],"Learning.":[147],"The":[148],"bootstrapped":[149],"RL-based":[150,179],"policy":[151,180],"gains":[152],"on":[153,181],"50":[155],"times":[156,166],"more":[157,167],"tested":[160],"simulation,":[162],"almost":[164],"18":[165],"interacting":[170],"users.":[173],"Users":[174],"also":[175,186],"subjectively":[176],"rate":[177],"10%":[183],"higher.":[184],"do":[193],"explicitly":[202],"stability":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}