{"id":"https://openalex.org/W192468626","doi":"https://doi.org/10.21437/interspeech.2007-707","title":"Hierarchical dialogue optimization using semi-Markov decision processes","display_name":"Hierarchical dialogue optimization using semi-Markov decision processes","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W192468626","doi":"https://doi.org/10.21437/interspeech.2007-707","mag":"192468626"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-707","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1842/1994","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036357777","display_name":"Heriberto Cuay\u00e1huitl","orcid":"https://orcid.org/0000-0002-1937-9837"},"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":"Heriberto Cuay\u00e1huitl","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"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":"Steve Renals","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010949145","display_name":"Oliver Lemon","orcid":"https://orcid.org/0000-0001-9497-4743"},"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":"Oliver Lemon","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062792381","display_name":"Hiroshi Shimodaira","orcid":"https://orcid.org/0000-0001-8956-2816"},"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":"Hiroshi Shimodaira","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2693","last_page":"2696"},"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9976999759674072,"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":0.9969000220298767,"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":0.9235334396362305},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8585152626037598},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.7718654870986938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7433974742889404},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6069629192352295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5693090558052063},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.541481077671051},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4949590563774109},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.49348723888397217},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4835371971130371},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4819221794605255},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.41800469160079956},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13844475150108337},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10474154353141785}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9235334396362305},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8585152626037598},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.7718654870986938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7433974742889404},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6069629192352295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5693090558052063},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.541481077671051},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4949590563774109},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.49348723888397217},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4835371971130371},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4819221794605255},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.41800469160079956},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13844475150108337},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10474154353141785},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2007-707","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},{"id":"pmh:oai:era.ed.ac.uk:1842/1994","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/1994","pdf_url":"http://hdl.handle.net/1842/1994","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","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":null,"raw_type":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.62.8013","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.62.8013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2007/SMDPs-interspeech2007.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:era.ed.ac.uk:1842/1994","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/1994","pdf_url":"http://hdl.handle.net/1842/1994","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","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":null,"raw_type":"Conference Paper"},"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W192468626.pdf","grobid_xml":"https://content.openalex.org/works/W192468626.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W36942980","https://openalex.org/W1530049455","https://openalex.org/W1582204956","https://openalex.org/W1586162706","https://openalex.org/W1592847719","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2132997613","https://openalex.org/W2158548602","https://openalex.org/W3011120880"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894"],"abstract_inverted_index":{"This":[0,34,123],"paper":[1,18],"addresses":[2],"the":[3,71,108],"problem":[4],"of":[5,47,85,119],"dialogue":[6,23,58,128,144],"optimization":[7,129],"on":[8,53],"large":[9],"search":[10,77],"spaces.":[11],"For":[12],"such":[13],"a":[14,45,54,75,93,112],"purpose,":[15],"in":[16,41,97],"this":[17],"we":[19],"propose":[20],"to":[21,43,127,131,138],"learn":[22,44],"strategies":[24],"using":[25],"multiple":[26],"Semi-Markov":[27],"Decision":[28],"Processes":[29],"and":[30,39,60,81,136],"hierarchical":[31,64,149],"reinforcement":[32,65,90,150],"learning.":[33,66,151],"approach":[35,73,124],"factorizes":[36],"state":[37],"variables":[38],"actions":[40],"order":[42],"hierarchy":[46],"policies.":[48],"Our":[49],"experiments":[50],"are":[51],"based":[52],"simulated":[55],"flight":[56],"booking":[57],"system":[59,102],"compare":[61],"flat":[62,89],"versus":[63],"Experimental":[67],"results":[68],"show":[69],"that":[70,107],"proposed":[72],"produced":[74],"dramatic":[76],"space":[78],"reduction":[79],"(99.36%),":[80],"converged":[82],"four":[83],"orders":[84],"magnitude":[86],"faster":[87,132],"than":[88],"learning":[91],"with":[92],"very":[94],"small":[95],"loss":[96],"optimality":[98],"(on":[99],"average":[100],"0.3":[101],"turns).":[103],"Results":[104],"also":[105],"report":[106],"learnt":[109],"policies":[110],"outperformed":[111],"hand-crafted":[113],"one":[114],"under":[115],"three":[116],"different":[117],"conditions":[118],"ASR":[120],"confidence":[121],"levels.":[122],"is":[125],"appealing":[126],"due":[130],"learning,":[133],"reusable":[134],"subsolutions,":[135],"scalability":[137],"larger":[139],"problems.":[140],"Index":[141],"Terms:":[142],"Spoken":[143],"systems,":[145],"semi-Markov":[146],"decision":[147],"processes,":[148]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}