{"id":"https://openalex.org/W2117578934","doi":"https://doi.org/10.1145/1228716.1228726","title":"Efficient model learning for dialog management","display_name":"Efficient model learning for dialog management","publication_year":2007,"publication_date":"2007-03-10","ids":{"openalex":"https://openalex.org/W2117578934","doi":"https://doi.org/10.1145/1228716.1228726","mag":"2117578934"},"language":"en","primary_location":{"id":"doi:10.1145/1228716.1228726","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1228716.1228726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE international conference on Human-robot interaction","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/40325","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041106414","display_name":"Finale Doshi","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":true,"raw_author_name":"Finale Doshi","raw_affiliation_strings":["CSAIL MIT, Cambridge, MA","CSAIL - MIT, Cambridge, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"CSAIL MIT, Cambridge, MA","institution_ids":[]},{"raw_affiliation_string":"CSAIL - MIT, Cambridge, MA, USA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010817303","display_name":"Nicholas Roy","orcid":"https://orcid.org/0000-0002-8293-0492"},"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":"Nicholas Roy","raw_affiliation_strings":["CSAIL MIT, Cambridge, MA","CSAIL - MIT, Cambridge, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"CSAIL MIT, Cambridge, MA","institution_ids":[]},{"raw_affiliation_string":"CSAIL - MIT, Cambridge, MA, USA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5041106414"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":9.6727,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":{"value":0.97867417,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"65","last_page":"72"},"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":0.9961000084877014,"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":0.9933000206947327,"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/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.8938944339752197},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.8906517624855042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8456515073776245},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.642217755317688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6147447824478149},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5610215067863464},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5535639524459839},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5457437038421631},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5362192392349243},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5356210470199585},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.5276264548301697},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4371325969696045},{"id":"https://openalex.org/keywords/user-modeling","display_name":"User modeling","score":0.41108179092407227},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3568922281265259},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35030049085617065},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.22603583335876465},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.20434561371803284},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.1423066258430481},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.079119473695755}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.8938944339752197},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.8906517624855042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8456515073776245},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.642217755317688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6147447824478149},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5610215067863464},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5535639524459839},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5457437038421631},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5362192392349243},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5356210470199585},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.5276264548301697},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4371325969696045},{"id":"https://openalex.org/C67712803","wikidata":"https://www.wikidata.org/wiki/Q7901853","display_name":"User modeling","level":3,"score":0.41108179092407227},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3568922281265259},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35030049085617065},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.22603583335876465},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.20434561371803284},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.1423066258430481},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.079119473695755},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/1228716.1228726","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1228716.1228726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE international conference on Human-robot interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.317.1907","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.317.1907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aaai.org/Papers/Symposia/Spring/2007/SS-07-07/SS07-07-002.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.323.668","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.323.668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.csail.mit.edu/finale/papers/SS07DoshiF.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.84.8947","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.84.8947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mapleleaf.csail.mit.edu/~nickroy/papers/hri07.pdf","raw_type":"text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/40325","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/40325","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":null,"raw_type":"Thesis"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/40325","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/40325","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":null,"raw_type":"Thesis"},"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W36713471","https://openalex.org/W37272079","https://openalex.org/W118038810","https://openalex.org/W166089536","https://openalex.org/W1220111186","https://openalex.org/W1484113995","https://openalex.org/W1491973539","https://openalex.org/W1496855202","https://openalex.org/W1497506444","https://openalex.org/W1501187080","https://openalex.org/W1526144783","https://openalex.org/W1532688806","https://openalex.org/W1539216098","https://openalex.org/W1547105496","https://openalex.org/W1565394148","https://openalex.org/W1582204956","https://openalex.org/W1600735390","https://openalex.org/W2007221309","https://openalex.org/W2076082451","https://openalex.org/W2099118758","https://openalex.org/W2100110221","https://openalex.org/W2109393574","https://openalex.org/W2111732304","https://openalex.org/W2116459397","https://openalex.org/W2119906889","https://openalex.org/W2125838338","https://openalex.org/W2129570755","https://openalex.org/W2134802714","https://openalex.org/W2144088174","https://openalex.org/W2147417895","https://openalex.org/W2156517809","https://openalex.org/W2161521419","https://openalex.org/W2166515056","https://openalex.org/W2169186423","https://openalex.org/W2438667436","https://openalex.org/W3011120880","https://openalex.org/W3101822862"],"related_works":["https://openalex.org/W48079147","https://openalex.org/W2394821827","https://openalex.org/W326836678","https://openalex.org/W4246582778","https://openalex.org/W2171219280","https://openalex.org/W2563921006","https://openalex.org/W1963944933","https://openalex.org/W2111550420","https://openalex.org/W4210962089","https://openalex.org/W2020240201"],"abstract_inverted_index":{"Intelligent":[0],"planning":[1,35],"algorithms":[2],"such":[3],"as":[4],"the":[5,26,44,48,81,97,106,119,129,151],"Partially":[6],"Observable":[7],"Markov":[8],"Decision":[9],"Process":[10],"(POMDP)":[11],"have":[12],"succeeded":[13],"in":[14,150,171,174],"dialog":[15,34,102,120,131,160],"management":[16],"applications":[17],"[10,":[18],"11,":[19],"12]":[20],"because":[21],"they":[22],"are":[23,55,68,154],"robust":[24,159],"to":[25,70,79,95,122,127,156],"inherent":[27],"uncertainty":[28],"of":[29,43,108],"human":[30],"interaction.":[31,152],"Like":[32],"all":[33],"systems,":[36],"however,":[37],"POMDPs":[38,54],"require":[39],"an":[40,112],"accurate":[41],"model":[42,62,99,170],"user":[45,49,98],"(e.g.,":[46],"what":[47],"might":[50],"say":[51],"or":[52],"want).":[53],"generally":[56],"specified":[57],"using":[58],"a":[59,84,92,142,158,168,175],"large":[60],"probabilistic":[61],"with":[63,101],"many":[64],"parameters.":[65],"These":[66],"parameters":[67,82],"difficult":[69],"specify":[71],"from":[72,135,164],"domain":[73],"knowledge,":[74],"and":[75,173],"gathering":[76],"enough":[77,126],"data":[78,134],"estimate":[80],"accurately":[83],"priori":[85],"is":[86,111],"expensive.In":[87],"this":[88],"paper,":[89],"we":[90],"take":[91],"Bayesian":[93],"approach":[94,110],"learning":[96],"simultaneously":[100],"manager":[103,121,161],"policy.":[104],"At":[105],"heart":[107],"our":[109],"efficient":[113],"incremental":[114],"update":[115,139],"algorithm":[116],"that":[117,162],"allows":[118],"replan":[123],"just":[124],"long":[125,148],"improve":[128],"current":[130],"policy":[132],"given":[133],"recent":[136],"interactions.":[137],"The":[138],"process":[140],"has":[141],"relatively":[143],"small":[144],"computational":[145],"cost,":[146],"preventing":[147],"delays":[149],"We":[153],"able":[155],"demonstrate":[157],"learns":[163],"interaction":[165],"data,":[166],"out-performing":[167],"hand-coded":[169],"simulation":[172],"robotic":[176],"wheelchair":[177],"application.":[178]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}