{"id":"https://openalex.org/W2914056350","doi":"https://doi.org/10.18653/v1/d19-5506","title":"Training on Synthetic Noise Improves Robustness to Natural Noise in Machine Translation","display_name":"Training on Synthetic Noise Improves Robustness to Natural Noise in Machine Translation","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2914056350","doi":"https://doi.org/10.18653/v1/d19-5506","mag":"2914056350"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d19-5506","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5506","pdf_url":"https://www.aclweb.org/anthology/D19-5506.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 5th Workshop on Noisy User-generated Text (W-NUT 2019)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D19-5506.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032508066","display_name":"Vladimir Karpukhin","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"vladimir karpukhin","raw_affiliation_strings":["Meta (Israel), Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024311574","display_name":"Omer Levy","orcid":"https://orcid.org/0000-0001-7300-8191"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Omer Levy","raw_affiliation_strings":["Stanford University, Stanford, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047699861","display_name":"Jacob Eisenstein","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Eisenstein","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, United States","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011974509","display_name":"Marjan Ghazvininejad","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Marjan Ghazvininejad","raw_affiliation_strings":["Meta (Israel), Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"42","last_page":"47"},"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":0.9958000183105469,"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":0.9695000052452087,"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/robustness","display_name":"Robustness (evolution)","score":0.8256188631057739},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7700376510620117},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6515215635299683},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.528801679611206},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4648778438568115},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4579538106918335},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4528256058692932},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43510016798973083},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4202577769756317}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8256188631057739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7700376510620117},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6515215635299683},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.528801679611206},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4648778438568115},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4579538106918335},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4528256058692932},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43510016798973083},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4202577769756317},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/d19-5506","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5506","pdf_url":"https://www.aclweb.org/anthology/D19-5506.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 5th Workshop on Noisy User-generated Text (W-NUT 2019)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1902.01509","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.01509","pdf_url":"https://arxiv.org/pdf/1902.01509","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:2914056350","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1902.01509","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.1902.01509","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1902.01509","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/d19-5506","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5506","pdf_url":"https://www.aclweb.org/anthology/D19-5506.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 5th Workshop on Noisy User-generated Text (W-NUT 2019)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5400000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2914056350.pdf","grobid_xml":"https://content.openalex.org/works/W2914056350.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2963661177","https://openalex.org/W2963403868","https://openalex.org/W2250539671","https://openalex.org/W2101105183","https://openalex.org/W2962784628","https://openalex.org/W2916835973","https://openalex.org/W3173485944","https://openalex.org/W2963532001","https://openalex.org/W2963250244","https://openalex.org/W2963216553","https://openalex.org/W2963122608","https://openalex.org/W2794365787","https://openalex.org/W2741177664","https://openalex.org/W3095052591","https://openalex.org/W2950764210","https://openalex.org/W3173220350","https://openalex.org/W1990165991","https://openalex.org/W2948805184","https://openalex.org/W1808888563","https://openalex.org/W3162820434"],"abstract_inverted_index":{"Contemporary":[0],"machine":[1],"translation":[2,58],"systems":[3],"achieve":[4],"greater":[5],"coverage":[6],"by":[7],"applying":[8],"subword":[9],"models":[10],"such":[11,26,68],"as":[12,27],"BPE":[13],"and":[14,63],"character-level":[15],"CNNs,":[16],"but":[17],"these":[18,47],"methods":[19],"are":[20],"highly":[21],"sensitive":[22],"to":[23,46,67,86],"orthographical":[24],"variations":[25],"spelling":[28],"mistakes.":[29],"We":[30,55],"show":[31,64],"how":[32],"training":[33,82],"on":[34,52,57,60],"a":[35,74],"mild":[36],"amount":[37],"of":[38,77],"random":[39],"synthetic":[40,79],"noise":[41,69,89],"can":[42,70],"dramatically":[43],"improve":[44],"robustness":[45,66],"variations,":[48],"without":[49,84],"diminishing":[50],"performance":[51,59],"clean":[53],"text.":[54],"focus":[56],"natural":[61,88],"typos,":[62],"that":[65],"be":[71],"achieved":[72],"using":[73],"balanced":[75],"diet":[76],"simple":[78],"noises":[80],"at":[81],"time,":[83],"access":[85],"the":[87],"data":[90],"or":[91],"distribution.":[92]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}