{"id":"https://openalex.org/W4319862687","doi":"https://doi.org/10.1109/slt54892.2023.10023191","title":"Building Markovian Generative Architectures Over Pretrained LM Backbones for Efficient Task-Oriented Dialog Systems","display_name":"Building Markovian Generative Architectures Over Pretrained LM Backbones for Efficient Task-Oriented Dialog Systems","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862687","doi":"https://doi.org/10.1109/slt54892.2023.10023191"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023191","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079533791","display_name":"Hong Liu","orcid":"https://orcid.org/0000-0002-2167-9396"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Liu","raw_affiliation_strings":["Tsinghua University,Speech Processing and Machine Intelligence (SPMI) Lab,Beijing,China","Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China","Tsinghua University-China Mobile Communications Group Co., Ltd. Joint Institute, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Speech Processing and Machine Intelligence (SPMI) Lab,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University-China Mobile Communications Group Co., Ltd. Joint Institute, Beijing, China","institution_ids":["https://openalex.org/I180662265","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050588540","display_name":"Yucheng Cai","orcid":"https://orcid.org/0009-0005-3764-5560"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yucheng Cai","raw_affiliation_strings":["Tsinghua University,Speech Processing and Machine Intelligence (SPMI) Lab,Beijing,China","Tsinghua University-China Mobile Communications Group Co., Ltd. Joint Institute, Beijing, China","Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Speech Processing and Machine Intelligence (SPMI) Lab,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University-China Mobile Communications Group Co., Ltd. Joint Institute, Beijing, China","institution_ids":["https://openalex.org/I180662265","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010173604","display_name":"Zhijian Ou","orcid":"https://orcid.org/0000-0002-9018-5074"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijian Ou","raw_affiliation_strings":["Tsinghua University,Speech Processing and Machine Intelligence (SPMI) Lab,Beijing,China","Tsinghua University-China Mobile Communications Group Co., Ltd. Joint Institute, Beijing, China","Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Speech Processing and Machine Intelligence (SPMI) Lab,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University-China Mobile Communications Group Co., Ltd. Joint Institute, Beijing, China","institution_ids":["https://openalex.org/I180662265","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101519937","display_name":"Yi Huang","orcid":"https://orcid.org/0000-0002-2169-9004"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Huang","raw_affiliation_strings":["China Mobile Research Institute,Beijing,China","Tsinghua University-China Mobile Communications Group Co., Ltd. Joint Institute, Beijing, China","China Mobile Research Institute, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Beijing,China","institution_ids":["https://openalex.org/I180662265"]},{"raw_affiliation_string":"Tsinghua University-China Mobile Communications Group Co., Ltd. Joint Institute, Beijing, China","institution_ids":["https://openalex.org/I180662265","https://openalex.org/I99065089"]},{"raw_affiliation_string":"China Mobile Research Institute, Beijing, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079750750","display_name":"Junlan Feng","orcid":"https://orcid.org/0000-0001-5292-2945"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlan Feng","raw_affiliation_strings":["China Mobile Research Institute,Beijing,China","Tsinghua University-China Mobile Communications Group Co., Ltd. Joint Institute, Beijing, China","China Mobile Research Institute, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Beijing,China","institution_ids":["https://openalex.org/I180662265"]},{"raw_affiliation_string":"Tsinghua University-China Mobile Communications Group Co., Ltd. Joint Institute, Beijing, China","institution_ids":["https://openalex.org/I180662265","https://openalex.org/I99065089"]},{"raw_affiliation_string":"China Mobile Research Institute, Beijing, China","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"382","last_page":"389"},"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":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962000250816345,"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":0.8207842111587524},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.6592541337013245},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.606808602809906},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6055867671966553},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.5490409135818481},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5185547471046448},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5178456902503967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45807573199272156},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4446055293083191},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44367292523384094},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4332486093044281},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07339087128639221}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8207842111587524},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.6592541337013245},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.606808602809906},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6055867671966553},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.5490409135818481},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5185547471046448},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5178456902503967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45807573199272156},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4446055293083191},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44367292523384094},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4332486093044281},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07339087128639221},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023191","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1932968309","https://openalex.org/W1975244201","https://openalex.org/W2468710617","https://openalex.org/W2749436976","https://openalex.org/W2798914047","https://openalex.org/W2963096017","https://openalex.org/W2963797754","https://openalex.org/W2964101860","https://openalex.org/W2979813451","https://openalex.org/W2997108628","https://openalex.org/W3021016503","https://openalex.org/W3034898894","https://openalex.org/W3098807778","https://openalex.org/W3126860450","https://openalex.org/W3156697766","https://openalex.org/W3185827732","https://openalex.org/W3196475603","https://openalex.org/W3201659492","https://openalex.org/W3214585123","https://openalex.org/W4243367687","https://openalex.org/W4287795696","https://openalex.org/W4288089799","https://openalex.org/W4288288848","https://openalex.org/W4294974598","https://openalex.org/W4385245566","https://openalex.org/W6640365096","https://openalex.org/W6718074661","https://openalex.org/W6739901393","https://openalex.org/W6743806204","https://openalex.org/W6766653659","https://openalex.org/W6769627184","https://openalex.org/W6770667678","https://openalex.org/W6771489201","https://openalex.org/W6789828710","https://openalex.org/W6800650279","https://openalex.org/W6801951456"],"related_works":["https://openalex.org/W1510894296","https://openalex.org/W2134386692","https://openalex.org/W2082284720","https://openalex.org/W2194396582","https://openalex.org/W2116722627","https://openalex.org/W2379938888","https://openalex.org/W2537260108","https://openalex.org/W4233405330","https://openalex.org/W2176285001","https://openalex.org/W2792905593"],"abstract_inverted_index":{"Recently,":[0],"Transformer":[1],"based":[2],"pretrained":[3],"language":[4],"models":[5,27,124,143],"(PLMs),":[6],"such":[7],"as":[8,40,94],"GPT2":[9],"and":[10,53,63,127],"T5,":[11],"have":[12],"been":[13],"leveraged":[14],"to":[15,99],"build":[16,100],"generative":[17],"task-oriented":[18],"dialog":[19,89],"(TOD)":[20],"systems.":[21,111],"A":[22],"drawback":[23],"of":[24,74,140],"existing":[25],"PLM-based":[26],"is":[28,38,144],"their":[29],"non-Markov":[30],"architectures":[31],"across":[32],"turns,":[33],"i.e.,":[34],"the":[35,41,57,66,86,118,121,134,137,141],"whole":[36,58],"history":[37,59],"used":[39],"conditioning":[42],"input":[43],"at":[44],"each":[45],"turn.":[46],"First,":[47],"this":[48,82],"brings":[49],"inefficiencies":[50],"in":[51,117,133],"memory":[52,126],"computation.":[54],"Furthermore,":[55],"using":[56],"increases":[60],"model":[61],"complexity":[62],"may":[64],"hurt":[65],"training":[67,76,138],"efficiency,":[68],"especially":[69],"when":[70],"facing":[71],"small":[72],"amounts":[73],"labeled":[75],"data":[77],"(the":[78],"low-resource":[79,135],"setting).":[80],"In":[81],"paper,":[83],"motivated":[84],"by":[85],"observation":[87],"that":[88,116],"states":[90],"could":[91],"be":[92],"viewed":[93],"Markov":[95,123,142],"states,":[96],"we":[97],"propose":[98],"Markovian":[101],"Generative":[102],"Architectures":[103],"(MGA)":[104],"over":[105],"PLM":[106],"backbones":[107],"for":[108],"efficient":[109],"TOD":[110],"Experiments":[112],"on":[113],"MultiWOZ2.1":[114],"show":[115],"rich-resource":[119],"setting,":[120,136],"proposed":[122],"reduce":[125],"time":[128],"costs":[129],"without":[130],"performance":[131],"degradation;":[132],"efficiency":[139],"more":[145],"significant.":[146]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}