{"id":"https://openalex.org/W3021992287","doi":null,"title":"When does data augmentation help generalization in NLP","display_name":"When does data augmentation help generalization in NLP","publication_year":2020,"publication_date":"2020-04-30","ids":{"openalex":"https://openalex.org/W3021992287","mag":"3021992287"},"language":"en","primary_location":{"id":"mag:3021992287","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/journals/corr/corr2004.html#abs-2004-15012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","indexed_in":[],"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/A5005578923","display_name":"Rohan Jha","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohan Jha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018940839","display_name":"Charles Lovering","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Charles Lovering","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053850863","display_name":"Ellie Pavlick","orcid":"https://orcid.org/0000-0002-7155-5420","observed_orcids":["https://orcid.org/0000-0002-7155-5420"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ellie Pavlick","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-7155-5420","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5893,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.70519507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.44699999690055847,"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":0.44699999690055847,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.20589999854564667,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.14710000157356262,"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/data-augmentation","display_name":"data augmentation","score":0.9990000128746033},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.9300000071525574},{"id":"https://openalex.org/keywords/counterexample","display_name":"counterexample","score":0.843999981880188},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.7770000100135803},{"id":"https://openalex.org/keywords/training-set-size","display_name":"training data size","score":0.47999998927116394}],"concepts":[{"id":"https://openalex.org/C162838799","wikidata":"https://www.wikidata.org/wiki/Q596077","display_name":"Counterexample","level":2,"score":0.8486915826797485},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7740886211395264},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7618700265884399},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7368518114089966},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.672626793384552},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6226775646209717},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6090937256813049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5827013850212097},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5279138088226318},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4847356975078583},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16549116373062134},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3021992287","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/journals/corr/corr2004.html#abs-2004-15012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1786845855","https://openalex.org/W2416885651","https://openalex.org/W2607892599","https://openalex.org/W2771951981","https://openalex.org/W2787708942","https://openalex.org/W2798139452","https://openalex.org/W2799007037","https://openalex.org/W2889468083","https://openalex.org/W2926555354","https://openalex.org/W2946794439","https://openalex.org/W2947469743","https://openalex.org/W2950866572","https://openalex.org/W2953369973","https://openalex.org/W2962717763","https://openalex.org/W2963526187","https://openalex.org/W2963969878","https://openalex.org/W2964204621","https://openalex.org/W2964253222","https://openalex.org/W2970115835","https://openalex.org/W2971015127","https://openalex.org/W2971089712"],"related_works":["https://openalex.org/W3092560821","https://openalex.org/W3130325649","https://openalex.org/W3041172414","https://openalex.org/W4412889907","https://openalex.org/W4389945783","https://openalex.org/W4402670893","https://openalex.org/W3103651020","https://openalex.org/W3176923149","https://openalex.org/W7171529382","https://openalex.org/W4401043512"],"abstract_inverted_index":{"Neural":[0],"models":[1,63],"often":[2,115],"exploit":[3],"superficial":[4],"(weak)":[5],"features":[6,18,57],"to":[7,24,64,77,123,142,173],"achieve":[8],"good":[9],"performance,":[10],"rather":[11],"than":[12],"deriving":[13],"the":[14,66,79,97,106,111,121,125,137,151,167],"more":[15],"general":[16],"(strong)":[17],"that":[19,90,136,157],"we'd":[20],"prefer":[21,65],"a":[22,30,59,71,144],"model":[23,107,122],"use.":[25],"Overcoming":[26],"this":[27,158],"tendency":[28],"is":[29,86,148],"central":[31],"challenge":[32],"in":[33,104,119,128,133],"areas":[34],"such":[35,83],"as":[36,166],"representation":[37],"learning":[38,75],"and":[39,156],"ML":[40],"fairness.":[41],"Recent":[42],"work":[43],"has":[44],"proposed":[45],"using":[46],"data":[47,84,161],"augmentation--that":[48],"is,":[49],"generating":[50],"training":[51,93,154],"examples":[52,94],"on":[53,95,110],"which":[54,82,96],"these":[55],"weak":[56,98,112],"fail--as":[58],"means":[60],"of":[61,73,139,150,153,160],"encouraging":[62,120],"stronger":[67,126],"features.":[68],"We":[69,88,130],"design":[70],"series":[72],"toy":[74],"problems":[76],"investigate":[78],"conditions":[80],"under":[81],"augmentation":[85,162],"helpful.":[87],"show":[89],"augmenting":[91],"with":[92],"feature":[99,127,170],"fails":[100],"(counterexamples)":[101],"does":[102,116],"succeed":[103,118],"preventing":[105],"from":[108],"relying":[109],"feature,":[113],"but":[114],"not":[117],"use":[124],"general.":[129],"also":[131],"find":[132],"many":[134],"cases":[135],"number":[138],"counterexamples":[140],"needed":[141],"reach":[143],"given":[145],"error":[146],"rate":[147],"independent":[149],"amount":[152],"data,":[155],"type":[159],"becomes":[163,171],"less":[164],"effective":[165],"target":[168],"strong":[169],"harder":[172],"learn.":[174]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2020-05-13T00:00:00"}