{"id":"https://openalex.org/W2888519496","doi":"https://doi.org/10.18653/v1/d18-1100","title":"SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation","display_name":"SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2888519496","doi":"https://doi.org/10.18653/v1/d18-1100","mag":"2888519496"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1100","pdf_url":"https://www.aclweb.org/anthology/D18-1100.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1100.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100382950","display_name":"Xinyi Wang","orcid":"https://orcid.org/0000-0002-6280-1300"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xinyi Wang","raw_affiliation_strings":["Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA 15213"],"affiliations":[{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA 15213","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101426340","display_name":"Hieu Pham","orcid":"https://orcid.org/0000-0001-7704-5053"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hieu Pham","raw_affiliation_strings":["Google Brain, Mountain View, CA 94043","Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA 15213"],"affiliations":[{"raw_affiliation_string":"Google Brain, Mountain View, CA 94043","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA 15213","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091869105","display_name":"Zihang Dai","orcid":"https://orcid.org/0000-0002-6509-5640"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zihang Dai","raw_affiliation_strings":["Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA 15213"],"affiliations":[{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA 15213","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068811427","display_name":"Graham Neubig","orcid":"https://orcid.org/0000-0002-2072-3789"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Graham Neubig","raw_affiliation_strings":["Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA 15213"],"affiliations":[{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA 15213","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100382950"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":18.0574,"has_fulltext":true,"cited_by_count":196,"citation_normalized_percentile":{"value":0.9929658,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"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/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9904999732971191,"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/machine-translation","display_name":"Machine translation","score":0.8677266836166382},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8375192880630493},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7025127410888672},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.688267707824707},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5988163352012634},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5868433713912964},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5580906271934509},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5515078902244568},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5195981860160828},{"id":"https://openalex.org/keywords/text-simplification","display_name":"Text simplification","score":0.42422235012054443},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4150266647338867},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.414650022983551},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34709590673446655},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10585859417915344},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07887205481529236}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8677266836166382},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8375192880630493},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7025127410888672},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.688267707824707},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5988163352012634},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5868433713912964},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5580906271934509},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5515078902244568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5195981860160828},{"id":"https://openalex.org/C59415355","wikidata":"https://www.wikidata.org/wiki/Q3484781","display_name":"Text simplification","level":3,"score":0.42422235012054443},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4150266647338867},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.414650022983551},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34709590673446655},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10585859417915344},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07887205481529236},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d18-1100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1100","pdf_url":"https://www.aclweb.org/anthology/D18-1100.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1100","pdf_url":"https://www.aclweb.org/anthology/D18-1100.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7599999904632568,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3429874898","display_name":null,"funder_award_id":"LORELEI","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2888519496.pdf","grobid_xml":"https://content.openalex.org/works/W2888519496.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W10980763","https://openalex.org/W1522301498","https://openalex.org/W1902237438","https://openalex.org/W2096175520","https://openalex.org/W2097117768","https://openalex.org/W2144600658","https://openalex.org/W2163605009","https://openalex.org/W2176263492","https://openalex.org/W2193413348","https://openalex.org/W2212703438","https://openalex.org/W2418388682","https://openalex.org/W2618606525","https://openalex.org/W2746314669","https://openalex.org/W2767206889","https://openalex.org/W2767899794","https://openalex.org/W2797913374","https://openalex.org/W2962801832","https://openalex.org/W2963216553","https://openalex.org/W2963248296","https://openalex.org/W2963266340","https://openalex.org/W2963403868","https://openalex.org/W2963446712","https://openalex.org/W2963661177","https://openalex.org/W2963708445","https://openalex.org/W2963962369","https://openalex.org/W2964121744","https://openalex.org/W2964137095","https://openalex.org/W3098341425","https://openalex.org/W3204406378","https://openalex.org/W4301230920","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3082178636","https://openalex.org/W1521968289","https://openalex.org/W2782041652","https://openalex.org/W2952088488","https://openalex.org/W2392157706","https://openalex.org/W2599192953","https://openalex.org/W2612657834","https://openalex.org/W2792147139","https://openalex.org/W2883671469","https://openalex.org/W4287855182"],"abstract_inverted_index":{"In":[0],"this":[1,83,123],"work,":[2],"we":[3],"examine":[4],"methods":[5],"for":[6,9,59],"data":[7,24,56],"augmentation":[8,25,47,57],"text-based":[10],"tasks":[11],"such":[12,112],"as":[13,30,113],"neural":[14],"machine":[15],"translation":[16,89],"(NMT).":[17],"We":[18,81],"formulate":[19],"the":[20,66,70,128],"design":[21],"of":[22,91,100],"a":[23,36],"policy":[26],"with":[27,73],"desirable":[28],"properties":[29],"an":[31,53],"optimization":[32],"problem,":[33],"and":[34,69],"derive":[35],"generic":[37],"analytic":[38],"solution.":[39],"This":[40],"solution":[41],"not":[42],"only":[43],"subsumes":[44],"some":[45],"existing":[46],"schemes,":[48],"but":[49],"also":[50],"leads":[51],"to":[52,109,121],"extremely":[54],"simple":[55],"strategy":[58],"NMT:":[60],"randomly":[61],"replacing":[62],"words":[63,76],"in":[64,127],"both":[65],"source":[67],"sentence":[68,72],"target":[71],"other":[74],"random":[75],"from":[77],"their":[78],"corresponding":[79],"vocabularies.":[80],"name":[82],"method":[84,124],"SwitchOut.":[85],"Experiments":[86],"on":[87],"three":[88],"datasets":[90],"different":[92],"scales":[93],"show":[94],"that":[95],"SwitchOut":[96],"yields":[97],"consistent":[98],"improvements":[99],"about":[101],"0.5":[102],"BLEU,":[103],"achieving":[104],"better":[105],"or":[106],"comparable":[107],"performances":[108],"strong":[110],"alternatives":[111],"word":[114],"dropout":[115],"(Sennrich":[116],"et":[117],"al.,":[118],"2016a).":[119],"Code":[120],"implement":[122],"is":[125],"included":[126],"appendix.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":28},{"year":2022,"cited_by_count":33},{"year":2021,"cited_by_count":48},{"year":2020,"cited_by_count":32},{"year":2019,"cited_by_count":26},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}