{"id":"https://openalex.org/W4386815555","doi":"https://doi.org/10.14428/esann/2023.es2023-42","title":"Rethink the Effectiveness of Text Data Augmentation: An Empirical Analysis","display_name":"Rethink the Effectiveness of Text Data Augmentation: An Empirical Analysis","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386815555","doi":"https://doi.org/10.14428/esann/2023.es2023-42"},"language":"en","primary_location":{"id":"doi:10.14428/esann/2023.es2023-42","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2023.es2023-42","pdf_url":"http://dx.doi.org/10.14428/esann/2023.es2023-42","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dx.doi.org/10.14428/esann/2023.es2023-42","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028607263","display_name":"Zhengxiang Shi","orcid":"https://orcid.org/0000-0003-3074-3035"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhengxiang Shi","raw_affiliation_strings":["University College London Gower St , London - United Kingdom","University College London Gower St, London -United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London Gower St , London - United Kingdom","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"University College London Gower St, London -United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058519912","display_name":"Aldo Lipani","orcid":"https://orcid.org/0000-0002-3643-6493"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Aldo Lipani","raw_affiliation_strings":["University College London Gower St , London - United Kingdom","University College London Gower St, London -United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London Gower St , London - United Kingdom","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"University College London Gower St, London -United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45129253"],"apc_list":null,"apc_paid":null,"fwci":0.617,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67779668,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"169","last_page":"174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8349207043647766},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.663739800453186},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5940693020820618},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5809295773506165},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5717460513114929},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5668029189109802},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.4873526990413666},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.47964149713516235},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.44946861267089844},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4211879372596741},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.421044260263443},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07257914543151855}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8349207043647766},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.663739800453186},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5940693020820618},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5809295773506165},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5717460513114929},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5668029189109802},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.4873526990413666},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.47964149713516235},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.44946861267089844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4211879372596741},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.421044260263443},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07257914543151855},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14428/esann/2023.es2023-42","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2023.es2023-42","pdf_url":"http://dx.doi.org/10.14428/esann/2023.es2023-42","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.14428/esann/2023.es2023-42","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2023.es2023-42","pdf_url":"http://dx.doi.org/10.14428/esann/2023.es2023-42","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386815555.pdf","grobid_xml":"https://content.openalex.org/works/W4386815555.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W2014902591","https://openalex.org/W2028175314","https://openalex.org/W2160660844","https://openalex.org/W2251939518","https://openalex.org/W2739351760","https://openalex.org/W2933138175","https://openalex.org/W2949380545","https://openalex.org/W2952186591","https://openalex.org/W2965373594","https://openalex.org/W3002104146","https://openalex.org/W3002151804","https://openalex.org/W3011396000","https://openalex.org/W3016590194","https://openalex.org/W3017961061","https://openalex.org/W3034238904","https://openalex.org/W3105959138","https://openalex.org/W3126960149","https://openalex.org/W3153427360","https://openalex.org/W3173777717","https://openalex.org/W3194325860","https://openalex.org/W3196642073","https://openalex.org/W4221138793","https://openalex.org/W4224253361","https://openalex.org/W4224266081","https://openalex.org/W4225665828","https://openalex.org/W4287025511","https://openalex.org/W4293248712","https://openalex.org/W4306935394","https://openalex.org/W4313908941","https://openalex.org/W4376166834","https://openalex.org/W4376864634","https://openalex.org/W4377865013","https://openalex.org/W4379473014","https://openalex.org/W4384659765","https://openalex.org/W4385567015","https://openalex.org/W4385571369"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W2375873920","https://openalex.org/W3151736118","https://openalex.org/W2146114872","https://openalex.org/W2392060890","https://openalex.org/W4362495644","https://openalex.org/W2392760275","https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W783305165"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"language":[3,16],"models":[4],"(LMs)":[5],"have":[6],"made":[7],"remarkable":[8],"progress":[9],"in":[10,52,123],"advancing":[11],"the":[12,19,27,45,83,101,105,108,115,124,130],"field":[13],"of":[14,21,31,38,47,59,85,104,117,132],"natural":[15],"processing":[17],"(NLP).However,":[18],"impact":[20],"data":[22,97],"augmentation":[23],"(DA)":[24],"techniques":[25],"on":[26,95],"finetuning":[28],"(FT)":[29],"performance":[30,103,116],"these":[32],"LMs":[33],"has":[34],"been":[35],"a":[36,135],"topic":[37],"ongoing":[39],"debate.In":[40],"this":[41],"study,":[42],"we":[43],"evaluate":[44],"effectiveness":[46],"three":[48],"different":[49],"FT":[50,87,102,118],"methods":[51],"conjugation":[53],"with":[54],"back-translation":[55],"across":[56],"an":[57],"array":[58],"7":[60],"diverse":[61],"NLP":[62],"tasks,":[63],"including":[64],"classification":[65],"and":[66,71],"regression":[67],"types,":[68],"covering":[69],"single-sentence":[70],"sentence-pair":[72],"tasks.Contrary":[73],"to":[74,82],"prior":[75],"assumptions":[76],"that":[77,92],"DA":[78,133],"does":[79],"not":[80],"contribute":[81],"enhancement":[84],"LMs'":[86,140],"performance,":[88],"our":[89],"findings":[90],"reveal":[91],"continued":[93,112],"pre-training":[94,113],"augmented":[96],"can":[98],"effectively":[99],"improve":[100],"downstream":[106],"tasks.In":[107],"most":[109],"favourable":[110],"case,":[111],"improves":[114],"by":[119],"more":[120],"than":[121],"10%":[122],"few-shot":[125],"learning":[126],"setting.Our":[127],"finding":[128],"highlights":[129],"potential":[131],"as":[134],"powerful":[136],"tool":[137],"for":[138],"bolstering":[139],"performance.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-08-22T07:34:49.880490","created_date":"2025-10-10T00:00:00"}