{"id":"https://openalex.org/W3193861091","doi":"https://doi.org/10.1145/3459637.3482229","title":"An Effective Non-Autoregressive Model for Spoken Language Understanding","display_name":"An Effective Non-Autoregressive Model for Spoken Language Understanding","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3193861091","doi":"https://doi.org/10.1145/3459637.3482229","mag":"3193861091"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3482229","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.07005","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lizhi Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lizhi Cheng","raw_affiliation_strings":["Shanghai JiaojinTong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai JiaojinTong University, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Weijia Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]},{"id":"https://openalex.org/I12615008","display_name":"Beijing Normal University - Hong Kong Baptist University United International College","ror":"https://ror.org/04snvc712","country_code":"CN","type":"education","lineage":["https://openalex.org/I12615008"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijia Jia","raw_affiliation_strings":["Beijing Normal University (BNU Zhuhai) & BNU-HKBU United International College, Zhuhai, China"],"affiliations":[{"raw_affiliation_string":"Beijing Normal University (BNU Zhuhai) & BNU-HKBU United International College, Zhuhai, China","institution_ids":["https://openalex.org/I12615008","https://openalex.org/I25254941"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wenmian Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenmian Yang","raw_affiliation_strings":["Shanghai JiaojinTong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai JiaojinTong University, Shanghai, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5398,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.86032906,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"241","last_page":"250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T12031","display_name":"Speech and dialogue systems","score":0.9987000226974487,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9965999722480774,"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/inference","display_name":"Inference","score":0.7767000198364258},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7301999926567078},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.6517000198364258},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5605999827384949},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5364000201225281},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5275999903678894},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5202999711036682},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5059000253677368},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.48089998960494995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922999858856201},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7767000198364258},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7301999926567078},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.6517000198364258},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5677000284194946},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5605999827384949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5479000210762024},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5364000201225281},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5275999903678894},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5202999711036682},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5059000253677368},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.48089998960494995},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4611000120639801},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3734999895095825},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2989000082015991},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2802000045776367},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C87868495","wikidata":"https://www.wikidata.org/wiki/Q750843","display_name":"Information processing","level":2,"score":0.250900000333786},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3459637.3482229","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.07005","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.07005","pdf_url":"https://arxiv.org/pdf/2108.07005","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2108.07005","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.07005","pdf_url":"https://arxiv.org/pdf/2108.07005","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2024632416","https://openalex.org/W2077302143","https://openalex.org/W2121879602","https://openalex.org/W2157331557","https://openalex.org/W2473329891","https://openalex.org/W2551571666","https://openalex.org/W2803392141","https://openalex.org/W2962775474","https://openalex.org/W2963594470","https://openalex.org/W2963925437","https://openalex.org/W2970450228","https://openalex.org/W2971167298","https://openalex.org/W3002918935","https://openalex.org/W3099757670","https://openalex.org/W3170264707"],"related_works":[],"abstract_inverted_index":{"Spoken":[0],"Language":[1],"Understanding":[2],"(SLU),":[3],"a":[4,13,56,66,73],"core":[5],"component":[6],"of":[7,21,39],"the":[8,19,28,37,83,88,97,116,129,157,161],"task-oriented":[9],"dialogue":[10],"system,":[11],"expects":[12],"shorter":[14],"inference":[15,29,158],"latency":[16],"due":[17],"to":[18,127],"impatience":[20],"humans.":[22],"Non-autoregressive":[23],"SLU":[24,59,118,143],"models":[25],"clearly":[26],"increase":[27],"speed":[30,151],"but":[31],"suffer":[32],"uncoordinated-slot":[33],"problems":[34],"caused":[35],"by":[36],"lack":[38],"sequential":[40],"dependency":[41,103],"information":[42,104],"among":[43],"each":[44],"slot":[45,85,93],"chunk.":[46],"To":[47],"gap":[48],"this":[49,52],"shortcoming,":[50],"in":[51,112],"paper,":[53],"we":[54],"propose":[55],"novel":[57],"non-autoregressive":[58,98],"model":[60,99,140],"named":[61],"Layered-Refine":[62],"Transformer,":[63],"which":[64],"contains":[65],"Slot":[67],"Label":[68],"Generation":[69],"(SLG)":[70],"task":[71],"and":[72,91,107,124],"Layered":[74],"Refine":[75],"Mechanism":[76],"(LRM).":[77],"SLG":[78],"is":[79],"defined":[80],"as":[81],"generating":[82],"next":[84],"label":[86],"with":[87],"token":[89],"sequence":[90],"generated":[92],"labels.":[94],"With":[95],"SLG,":[96],"can":[100],"efficiently":[101],"obtain":[102],"during":[105],"training":[106],"spend":[108],"no":[109],"extra":[110],"time":[111],"inference.":[113],"LRM":[114],"predicts":[115],"preliminary":[117],"results":[119],"from":[120],"Transformer's":[121],"middle":[122],"states":[123],"utilizes":[125],"them":[126],"guide":[128],"final":[130],"prediction.":[131],"Experiments":[132],"on":[133,146],"two":[134],"public":[135],"datasets":[136],"indicate":[137],"that":[138],"our":[139],"significantly":[141],"improves":[142],"performance":[144],"(1.5%":[145],"Overall":[147],"accuracy)":[148],"while":[149],"substantially":[150],"up":[152],"(more":[153],"than":[154],"10":[155],"times)":[156],"process":[159],"over":[160],"state-of-the-art":[162],"baseline.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2021-08-30T00:00:00"}