{"id":"https://openalex.org/W3047199820","doi":"https://doi.org/10.21437/interspeech.2020-1676","title":"Data Balancing for Boosting Performance of Low-Frequency Classes in Spoken Language Understanding","display_name":"Data Balancing for Boosting Performance of Low-Frequency Classes in Spoken Language Understanding","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3047199820","doi":"https://doi.org/10.21437/interspeech.2020-1676","mag":"3047199820"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1676","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.02603","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026722932","display_name":"Judith Gaspers","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Judith Gaspers","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031943883","display_name":"Quynh Do","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quynh Do","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051677043","display_name":"Fabian Triefenbach","orcid":null},"institutions":[{"id":"https://openalex.org/I2801227569","display_name":"Ghent University Hospital","ror":"https://ror.org/00xmkp704","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801227569"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Fabian Triefenbach","raw_affiliation_strings":["Ghent University, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I2801227569"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1560","last_page":"1564"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9945999979972839,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8292789459228516},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6579675674438477},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5954888463020325},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.49909305572509766},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4797957241535187},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4716222286224365},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4594711661338806},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.44431233406066895},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43781036138534546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43512290716171265},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38363972306251526}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8292789459228516},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6579675674438477},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5954888463020325},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.49909305572509766},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4797957241535187},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4716222286224365},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4594711661338806},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.44431233406066895},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43781036138534546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43512290716171265},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38363972306251526},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-1676","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.02603","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.02603","pdf_url":"https://arxiv.org/pdf/2008.02603","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"},{"id":"mag:3047199820","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2008.02603.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2008.02603","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.02603","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.02603","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.02603","pdf_url":"https://arxiv.org/pdf/2008.02603","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":[{"id":"https://metadata.un.org/sdg/4","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3047199820.pdf","grobid_xml":"https://content.openalex.org/works/W3047199820.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2053724458","https://openalex.org/W2097550833","https://openalex.org/W2148143831","https://openalex.org/W2148708890","https://openalex.org/W2165910495","https://openalex.org/W2440599146","https://openalex.org/W2469885745","https://openalex.org/W2562319768","https://openalex.org/W2753300133","https://openalex.org/W2778814079","https://openalex.org/W2803392141","https://openalex.org/W2810417023","https://openalex.org/W2899434936","https://openalex.org/W2917128112","https://openalex.org/W2927258315","https://openalex.org/W2945892998","https://openalex.org/W2962772844","https://openalex.org/W2963341956","https://openalex.org/W2963703197","https://openalex.org/W2963974889","https://openalex.org/W2970941190"],"related_works":["https://openalex.org/W3095182278","https://openalex.org/W2980748755","https://openalex.org/W3166785322","https://openalex.org/W3213485676","https://openalex.org/W3119896582","https://openalex.org/W2288707378","https://openalex.org/W3168428105","https://openalex.org/W3028630157","https://openalex.org/W3199483798","https://openalex.org/W3135990190","https://openalex.org/W2594940144","https://openalex.org/W188614264","https://openalex.org/W3206407025","https://openalex.org/W3005469290","https://openalex.org/W3200511797","https://openalex.org/W3044482206","https://openalex.org/W3186833834","https://openalex.org/W2573242108","https://openalex.org/W2975381464","https://openalex.org/W3083853483"],"abstract_inverted_index":{"Despite":[0],"the":[1,26,29,37,51,129,162,173,186],"fact":[2],"that":[3,109],"data":[4,43,55,81,134,143,155,160],"imbalance":[5,44],"is":[6],"becoming":[7],"more":[8,10],"and":[9,60,69,98,178],"common":[11],"in":[12,25,76,161,180],"real-world":[13,106],"Spoken":[14],"Language":[15],"Understanding":[16],"(SLU)":[17],"applications,":[18],"it":[19],"has":[20],"not":[21,145,191],"been":[22],"studied":[23],"extensively":[24],"literature.":[27],"To":[28],"best":[30],"of":[31,53,93,153],"our":[32,77,111],"knowledge,":[33],"this":[34],"paper":[35],"presents":[36],"first":[38],"systematic":[39],"study":[40],"on":[41,104,117,128],"handling":[42],"for":[45,58,66,80,137],"SLU.":[46],"In":[47],"particular,":[48],"we":[49],"discuss":[50],"application":[52],"existing":[54],"balancing":[56,82,185],"techniques":[57],"SLU":[59,64],"propose":[61],"a":[62,94,105,124,150,181],"multi-task":[63],"model":[65,78,113],"intent":[67,187,193],"classification":[68,194],"slot":[70,197],"filling.":[71],"Aiming":[72],"to":[73,172],"avoid":[74],"over-fitting,":[75],"methods":[79],"are":[83,135,144],"leveraged":[84],"indirectly":[85],"via":[86],"an":[87],"auxiliary":[88,163],"task":[89,164,175],"which":[90],"makes":[91],"use":[92],"class-balanced":[95],"batch":[96],"generator":[97],"(possibly)":[99],"synthetic":[100,133,159],"data.":[101],"Our":[102],"results":[103],"dataset":[107],"indicate":[108],"i)":[110],"proposed":[112],"can":[114],"boost":[115],"performance":[116,126,168],"low":[118],"frequency":[119],"intents":[120,140],"significantly":[121],"while":[122],"avoiding":[123],"potential":[125],"decrease":[127],"head":[130],"intents,":[131],"ii)":[132],"beneficial":[136],"bootstrapping":[138],"new":[139],"when":[141],"realistic":[142,154],"available,":[146,157],"but":[147,195],"iii)":[148],"once":[149],"certain":[151],"amount":[152],"becomes":[156],"using":[158],"only":[165,192],"yields":[166],"better":[167],"than":[169],"adding":[170],"them":[171],"primary":[174],"training":[176,183],"data,":[177],"iv)":[179],"joint":[182],"scenario,":[184],"distribution":[188],"individually":[189],"improves":[190],"also":[196],"filling":[198],"performance.":[199]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-07-26T00:00:00"}