An analysis of Google Translate and DeepL translation of source text typographical errors in the economic and legal fields

An analysis of Google Translate and DeepL translation of source text typographical errors in the economic and legal fields

Training neural machine translation systems with noisy data has been shown to improve robustness (Heigold et al., 2018). The objective of the present study is to test Google Translate and DeepL performance in the detection and correction of typographical errors, by introducing 1,820 source text typo...

Full description

Saved in:
Bibliographic Details
Published in:Revista de llengua i dret pp. 88 - 105
Main Author: Santiago Rodríguez-Rubio Mediavilla
Format: Journal Article
Language:Aragonese Spanish
English
Published: Escola d'Administració Pública de Catalunya 01-06-2024
Subjects:
deepl
google translate
neural machine translation
specialised texts
translation
typographical errors
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Training neural machine translation systems with noisy data has been shown to improve robustness (Heigold et al., 2018). The objective of the present study is to test Google Translate and DeepL performance in the detection and correction of typographical errors, by introducing 1,820 source text typos found in a previous work on specialised Spanish-English dictionaries (Rodríguez-Rubio & Fernández-Quesada, 2020a, 2020b; Rodríguez-Rubio Mediavilla, 2021). Typos were introduced in isolation and also in co-text. Results showed that Google Translate clearly outperformed DeepL. Moreover, the repetition of the source typo was found to be the most frequent phenomenon in the machine translation output of both systems. By shedding light on the capacity of systems to deal with source text typographical errors, our study aims to provide a starting point for their refinement.
AbstractList Training neural machine translation systems with noisy data has been shown to improve robustness (Heigold et al., 2018). The objective of the present study is to test Google Translate and DeepL performance in the detection and correction of typographical errors, by introducing 1,820 source text typos found in a previous work on specialised Spanish-English dictionaries (Rodríguez-Rubio & Fernández-Quesada, 2020a, 2020b; Rodríguez-Rubio Mediavilla, 2021). Typos were introduced in isolation and also in co-text. Results showed that Google Translate clearly outperformed DeepL. Moreover, the repetition of the source typo was found to be the most frequent phenomenon in the machine translation output of both systems. By shedding light on the capacity of systems to deal with source text typographical errors, our study aims to provide a starting point for their refinement.
Author Santiago Rodríguez-Rubio Mediavilla
Author_xml – sequence: 1
  fullname: Santiago Rodríguez-Rubio Mediavilla
BookMark eNotjc1OAjEUhRuDiYi8gKu-wGD_ZnpnSVCRhMQNrielvYWaMiXtmIhPLyKrk3znyzn3ZNSnHgl55GxWQ9uKpxzdLACfCSbUTHGAGzIWjMuKq1qOyJgJLqqa1c0dmZYStkw0reYgYEx-5j01vYmnEgpNni5T2kWkm2z6Es2A59LRZ8Tjmg5XFlL_Z5b0lS3SAb8HOpyOaZfNcR-siRRzTrnQ0NNhjxRt6tMh2MtSxN1Z8AGjKw_k1ptYcHrNCfl4fdks3qr1-3K1mK8rx2s-VN612oPdGvAASmjHGPeuqZlDplBapVUjpa8t2LMKYGspNTbSKKWlVFZOyOp_1yXz2R1zOJh86pIJ3QWkvOtMHoKN2DEtUTfeaAlKgZatgfPTttEAWimr5S8gz3Bh
ContentType Journal Article
DBID DOA
DOI 10.58992/rld.i81.2024.4188
DatabaseName Directory of Open Access Journals
DatabaseTitleList
Database_xml – sequence: 1
  dbid: DOA
  name: Directory of Open Access Journals
  url: http://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Languages & Literatures
EISSN 2013-1453
EndPage 105
ExternalDocumentID oai_doaj_org_article_073e76fa738448739a8d65b6788744c7
GroupedDBID .4L
1XV
2VB
ADBBV
ALMA_UNASSIGNED_HOLDINGS
BCNDV
EBS
EJD
GROUPED_DOAJ
HEY
KQ8
OK1
RNS
~Y0
ID FETCH-LOGICAL-d151t-fd97f8cba8f88427d001fd650de04e3c474633f5c8cfd988c5337e63a447334c3
IEDL.DBID DOA
ISSN 0212-5056
IngestDate Tue Oct 22 15:16:54 EDT 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed false
IsScholarly true
Language Aragonese
English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-d151t-fd97f8cba8f88427d001fd650de04e3c474633f5c8cfd988c5337e63a447334c3
OpenAccessLink https://doaj.org/article/073e76fa738448739a8d65b6788744c7
PageCount 18
ParticipantIDs doaj_primary_oai_doaj_org_article_073e76fa738448739a8d65b6788744c7
PublicationCentury 2000
PublicationDate 2024-06-01
PublicationDateYYYYMMDD 2024-06-01
PublicationDate_xml – month: 06
  year: 2024
  text: 2024-06-01
  day: 01
PublicationDecade 2020
PublicationTitle Revista de llengua i dret
PublicationYear 2024
Publisher Escola d'Administració Pública de Catalunya
Publisher_xml – name: Escola d'Administració Pública de Catalunya
SSID ssib026971828
ssj0000498125
Score 2.3141017
Snippet Training neural machine translation systems with noisy data has been shown to improve robustness (Heigold et al., 2018). The objective of the present study is...
SourceID doaj
SourceType Open Website
StartPage 88
SubjectTerms deepl
google translate
neural machine translation
specialised texts
translation
typographical errors
Title An analysis of Google Translate and DeepL translation of source text typographical errors in the economic and legal fields
URI https://doaj.org/article/073e76fa738448739a8d65b6788744c7
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://sdu.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV09T8MwELWgEwvi-xvdgNjSJrEdO2OBlg4VCyCxRYk_UFGVVEk6wK_nHEdVNxZWx7Eiv1PeO-vumZC7otCUa84DWwgRMG1UUMRcBawoWBRaFRrtjgZmr-LlQz5NnE3O5qovVxPm7YH9xo0wBI1IbC6oxExC0DSXOuFF4qrgGFO-jzxMt5IpjKQ4SfGf2wvrL6-Dkcm6esbYmf8j7fsOGo75Rjyql3q4kC5djNmQRe4ali0H_45qpgdkv9eIMPbfdkh28vKInM37k8UG7mG-MUNujsnPuIS89xaBysJzVX0uDXQstEQpiQ81PBmzmkPbjyEYbqY_uQdX_AHt98q7VzvUwNR1VTewKAEFIpi-e7lbaWmQVKCrfGtOyPt08vY4C_orFQKN1N4GVqfCSlXk0krJYqGRpSzuZ6hNyAxVTLCEUsuVVDhVSoVqUJiE5owJSpmip2RQVqU5J8BdMhJKKyKdoiaL8iiVBle03OKLVlyQB7eF2cq7ZmTOx7obQHSzHt3sL3Qv_2ORK7LngPUFXtdk0NZrc0N2G72-7aLmF4cZwzQ
link.rule.ids 315,783,787,867,2109,27936,27937
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=An+analysis+of+Google+Translate+and+DeepL+translation+of+source+text+typographical+errors+in+the+economic+and+legal+fields&rft.jtitle=Revista+de+llengua+i+dret&rft.au=Santiago+Rodr%C3%ADguez-Rubio+Mediavilla&rft.date=2024-06-01&rft.pub=Escola+d%27Administraci%C3%B3+P%C3%BAblica+de+Catalunya&rft.issn=0212-5056&rft.eissn=2013-1453&rft.spage=88&rft.epage=105&rft_id=info:doi/10.58992%2Frld.i81.2024.4188&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_073e76fa738448739a8d65b6788744c7
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0212-5056&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0212-5056&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0212-5056&client=summon