{"id":"https://openalex.org/W2986712369","doi":"https://doi.org/10.18653/v1/d19-5543","title":"Improving Neural Machine Translation Robustness via Data Augmentation: Beyond Back-Translation","display_name":"Improving Neural Machine Translation Robustness via Data Augmentation: Beyond Back-Translation","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2986712369","doi":"https://doi.org/10.18653/v1/d19-5543","mag":"2986712369"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5543","pdf_url":"https://www.aclweb.org/anthology/D19-5543.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"preprint","type_crossref":"proceedings-article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.aclweb.org/anthology/D19-5543.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027358109","display_name":"Zhenhao Li","orcid":"https://orcid.org/0000-0001-7506-9967"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhenhao Li","raw_affiliation_strings":["Department of Computing Imperial College London, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computing Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053217291","display_name":"Lucia Specia","orcid":"https://orcid.org/0000-0002-5495-3128"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lucia Specia","raw_affiliation_strings":["Department of Computing Imperial College London, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computing Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":22,"citation_normalized_percentile":{"value":0.999926,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":92,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9997,"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":0.9879,"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/robustness","display_name":"Robustness","score":0.859332},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.68122435},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43067762}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.859332},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.84620947},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8028159},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.68122435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5195289},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44183293},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43067762},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.41560376},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3779231},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32798186},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5543","pdf_url":"https://www.aclweb.org/anthology/D19-5543.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1910.03009","pdf_url":"https://arxiv.org/pdf/1910.03009","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://hdl.handle.net/10044/1/79499","pdf_url":"http://spiral.imperial.ac.uk/bitstream/10044/1/79499/7/D19-5543.pdf","source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":["Imperial College London"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://api.datacite.org/dois/10.48550/arxiv.1910.03009","pdf_url":null,"source":{"id":"https://openalex.org/S4393179698","display_name":"DataCite API","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210145204","host_organization_name":"DataCite","host_organization_lineage":["https://openalex.org/I4210145204"],"host_organization_lineage_names":["DataCite"],"type":"metadata"},"license":null,"license_id":null,"version":null}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5543","pdf_url":"https://www.aclweb.org/anthology/D19-5543.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":["https://openalex.org/W2986712369","https://openalex.org/W3101990291"],"referenced_works_count":33,"referenced_works":["https://openalex.org/W1647671624","https://openalex.org/W2101105183","https://openalex.org/W2124807415","https://openalex.org/W2133564696","https://openalex.org/W2184135559","https://openalex.org/W2580723344","https://openalex.org/W2595715041","https://openalex.org/W2613904329","https://openalex.org/W2767899794","https://openalex.org/W2945700568","https://openalex.org/W2952317054","https://openalex.org/W2962784628","https://openalex.org/W2963122608","https://openalex.org/W2963212250","https://openalex.org/W2963216553","https://openalex.org/W2963403868","https://openalex.org/W2963661177","https://openalex.org/W2963823140","https://openalex.org/W2964048171","https://openalex.org/W2964247056","https://openalex.org/W2964308564","https://openalex.org/W2970015022","https://openalex.org/W2970169061","https://openalex.org/W2970250638","https://openalex.org/W2970336035","https://openalex.org/W2970558573","https://openalex.org/W2970798168","https://openalex.org/W2970926924","https://openalex.org/W2971078337","https://openalex.org/W2971134989","https://openalex.org/W2984051011","https://openalex.org/W4300835687","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W783305165","https://openalex.org/W4289548080","https://openalex.org/W4285877427","https://openalex.org/W3173587717","https://openalex.org/W3165456129","https://openalex.org/W2972060578","https://openalex.org/W2963642612","https://openalex.org/W2883671469","https://openalex.org/W160673860","https://openalex.org/W1585680390"],"abstract_inverted_index":{"Neural":[0],"Machine":[1,41],"Translation":[2,42],"(NMT)":[3],"models":[4,25,107],"have":[5],"been":[6],"proved":[7],"strong":[8],"when":[9],"translating":[10],"clean":[11],"texts,":[12],"but":[13,57],"they":[14],"are":[15,70],"very":[16,61],"sensitive":[17],"to":[18,36,92,102],"noise":[19,103,116],"in":[20,63,120],"the":[21,106,112,121],"input.":[22],"Improving":[23],"NMT":[24,100],"robustness":[26,101],"can":[27],"be":[28],"seen":[29],"as":[30],"a":[31,53],"form":[32,122],"of":[33,76,114,123],"\"domain\"":[34],"adaption":[35],"noise.":[37],"The":[38,67],"recently":[39],"created":[40],"on":[43,73],"Noisy":[44],"Text":[45],"task":[46],"corpus":[47],"provides":[48],"noisy-clean":[49],"parallel":[50],"data":[51,59,89,96,119],"for":[52],"few":[54],"language":[55],"pairs,":[56],"this":[58],"is":[60],"limited":[62,94],"size":[64],"and":[65,97,126],"diversity.":[66],"state-of-the-art":[68],"approaches":[69],"heavily":[71],"dependent":[72],"large":[74],"volumes":[75],"back-translated":[77],"data.":[78],"This":[79],"paper":[80],"has":[81],"two":[82],"main":[83],"contributions:":[84],"Firstly,":[85],"we":[86,110],"propose":[87],"new":[88],"augmentation":[90],"methods":[91],"extend":[93],"noisy":[95],"further":[98],"improve":[99],"while":[104],"keeping":[105],"small.":[108],"Secondly,":[109],"explore":[111],"effect":[113],"utilizing":[115],"from":[117],"external":[118],"speech":[124],"transcripts":[125],"show":[127],"that":[128],"it":[129],"could":[130],"help":[131],"robustness.":[132]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2986712369","counts_by_year":[{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2025-01-07T17:46:41.413864","created_date":"2019-11-22"}