{"id":"https://openalex.org/W2979308242","doi":"https://doi.org/10.18653/v1/d19-6101","title":"A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classification","display_name":"A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classification","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2979308242","doi":"https://doi.org/10.18653/v1/d19-6101","mag":"2979308242"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d19-6101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6101","pdf_url":"https://www.aclweb.org/anthology/D19-6101.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D19-6101.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103330992","display_name":"Varun Kumar","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"]},{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Varun Kumar","raw_affiliation_strings":["Amazon Alexa Cambridge, MA, USA","Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080320000","display_name":"Hadrien Glaude","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"]},{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Hadrien Glaude","raw_affiliation_strings":["Amazon Alexa Cambridge, MA, USA","Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002839958","display_name":"Cyprien de Lichy","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"]},{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Cyprien de Lichy","raw_affiliation_strings":["Amazon Alexa Cambridge, MA, USA","Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061064027","display_name":"William M. Campbell","orcid":"https://orcid.org/0000-0003-1657-5872"},"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"]},{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Wlliam Campbell","raw_affiliation_strings":["Amazon Alexa Cambridge, MA, USA","Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1569,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84592825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9976000189781189,"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":0.9972000122070312,"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":0.7830468416213989},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.6880167722702026},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.650568962097168},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6136040687561035},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.6063743829727173},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5785542130470276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5680627226829529},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.5283730030059814},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5246974229812622},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5091440081596375},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.49660855531692505},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.46896564960479736},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.46740180253982544},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10301920771598816},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10130992531776428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7830468416213989},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.6880167722702026},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.650568962097168},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6136040687561035},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.6063743829727173},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5785542130470276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5680627226829529},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.5283730030059814},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5246974229812622},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5091440081596375},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.49660855531692505},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.46896564960479736},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.46740180253982544},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10301920771598816},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10130992531776428},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/d19-6101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6101","pdf_url":"https://www.aclweb.org/anthology/D19-6101.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.04176","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.04176","pdf_url":"https://arxiv.org/pdf/1910.04176","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:2979308242","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.04176","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.1910.04176","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.04176","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/d19-6101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6101","pdf_url":"https://www.aclweb.org/anthology/D19-6101.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2979308242.pdf","grobid_xml":"https://content.openalex.org/works/W2979308242.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2023639956","https://openalex.org/W2148143831","https://openalex.org/W2270409809","https://openalex.org/W2516907570","https://openalex.org/W2601450892","https://openalex.org/W2604297385","https://openalex.org/W2604763608","https://openalex.org/W2742093937","https://openalex.org/W2753160622","https://openalex.org/W2770173563","https://openalex.org/W2787560479","https://openalex.org/W2803392141","https://openalex.org/W2803609229","https://openalex.org/W2810809989","https://openalex.org/W2888026659","https://openalex.org/W2891051852","https://openalex.org/W2892122929","https://openalex.org/W2912154624","https://openalex.org/W2921156067","https://openalex.org/W2946411231","https://openalex.org/W2949500715","https://openalex.org/W2951004968","https://openalex.org/W2951751045","https://openalex.org/W2953082503","https://openalex.org/W2962772844","https://openalex.org/W2963018920","https://openalex.org/W2963078860","https://openalex.org/W2963329574","https://openalex.org/W2963341924","https://openalex.org/W2963341956","https://openalex.org/W2963845150","https://openalex.org/W2964249870","https://openalex.org/W2964316912","https://openalex.org/W2970655599","https://openalex.org/W3091905774"],"related_works":["https://openalex.org/W2985353426","https://openalex.org/W3090245986","https://openalex.org/W3105502848","https://openalex.org/W3170116649","https://openalex.org/W3209038819","https://openalex.org/W2804107505","https://openalex.org/W3034987881","https://openalex.org/W3174036215","https://openalex.org/W3163412989","https://openalex.org/W2969666864","https://openalex.org/W3109858448","https://openalex.org/W2971048662","https://openalex.org/W3184618274","https://openalex.org/W3212893438","https://openalex.org/W2946423414","https://openalex.org/W3115913034","https://openalex.org/W3021669159","https://openalex.org/W3098611607","https://openalex.org/W2979714393","https://openalex.org/W2904389022"],"abstract_inverted_index":{"New":[0],"conversation":[1],"topics":[2],"and":[3,16,22,27,91,108],"functionalities":[4,39],"are":[5,40,61],"constantly":[6],"being":[7],"added":[8],"to":[9,63,79,125,163],"conversational":[10,105],"AI":[11],"agents":[12],"like":[13],"Amazon":[14],"Alexa":[15],"Apple":[17],"Siri.":[18],"As":[19],"data":[20,76,116,172],"collection":[21],"annotation":[23],"is":[24,28,148,167],"not":[25],"scalable":[26],"often":[29],"costly,":[30],"only":[31],"a":[32,52,58,65,149,164,168],"handful":[33],"of":[34],"examples":[35,60,162],"for":[36,152],"the":[37,109,158],"new":[38,66,165],"available,":[41],"which":[42],"results":[43],"in":[44,83,86,118,130,145],"poor":[45],"generalization":[46],"performance.":[47],"We":[48],"formulate":[49],"it":[50],"as":[51,97],"Few-Shot":[53],"Integration":[54],"(FSI)":[55],"problem":[56],"where":[57],"few":[59],"used":[62],"introduce":[64],"intent.":[67],"In":[68,138],"this":[69],"paper,":[70],"we":[71,113,140],"study":[72],"six":[73],"feature":[74,119,153],"space":[75,120,147,154],"augmentation":[77,117,155,173],"methods":[78,95],"improve":[80,126],"classification":[81,128],"performance":[82,129],"FSI":[84],"setting":[85,132],"combination":[87],"with":[88],"both":[89],"supervised":[90],"unsupervised":[92],"representation":[93],"learning":[94,136],"such":[96],"BERT.":[98],"Through":[99],"realistic":[100],"experiments":[101],"on":[102],"two":[103,161],"public":[104],"datasets,":[106],"SNIPS,":[107],"Facebook":[110],"Dialog":[111],"corpus,":[112],"show":[114,141],"that":[115,142],"provides":[121],"an":[122],"effective":[123,171],"way":[124],"intent":[127],"fewshot":[131],"beyond":[133],"traditional":[134],"transfer":[135],"approaches.":[137],"particular,":[139],"(a)":[143],"upsampling":[144],"latent":[146],"competitive":[150],"baseline":[151],"(b)":[156],"adding":[157],"difference":[159],"between":[160],"example":[166],"simple":[169],"yet":[170],"method.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}