Translation Quality, Quality Management and Agency: Principles and Practice in the European Union Institutions

Drugan, Joanna; Strandvik, Ingemar; Vuorinen, Erkka

doi:10.1007/978-3-319-91241-7_3

Cited by 10 publications

(10 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This intervention is generally referred to as post-editing. Moreover, in a context where translation quality requirements are extremely high (in the case of DGT for example translated texts are often legally binding [4]), even perfect MT suggestions have to be approved by human translators. Measuring the effect of MT thus basically boils down to measuring how humans interact with the MT suggestions, or, phrased differently, to measuring the human effort needed to adapt an MT suggestion to meet the required quality standards.…”

Section: Related Researchmentioning

confidence: 99%

Quantifying the Effect of Machine Translation in a High-Quality Human Translation Production Process

2020

View full text Add to dashboard Cite

This paper studies the impact of machine translation (MT) on the translation workflow at the Directorate-General for Translation (DGT), focusing on two language pairs and two MT paradigms: English-into-French with statistical MT and English-into-Finnish with neural MT. We collected data from 20 professional translators at DGT while they carried out real translation tasks in normal working conditions. The participants enabled/disabled MT for half of the segments in each document. They filled in a survey at the end of the logging period. We measured the productivity gains (or losses) resulting from the use of MT and examined the relationship between technical effort and temporal effort. The results show that while the usage of MT leads to productivity gains on average, this is not the case for all translators. Moreover, the two technical effort indicators used in this study show weak correlations with post-editing time. The translators’ perception of their speed gains was more or less in line with the actual results. Reduction of typing effort is the most frequently mentioned reason why participants preferred working with MT, but also the psychological benefits of not having to start from scratch were often mentioned.

show abstract

Section: Related Researchmentioning

confidence: 99%

Quantifying the Effect of Machine Translation in a High-Quality Human Translation Production Process

2020

View full text Add to dashboard Cite

show abstract

“…The standard contains 21 translation parameters divided into five categories (source content, requirements for the target, production tasks, environment, and relationships). In addition to the ISO standards, the European Commission's Directorate-General for Translation also sets good standards for translation quality (Drugan et al, 2018), at least for institutional circumstances.…”

Section: Industry Approachesmentioning

confidence: 99%

A reception study of machine translated subtitles for MOOCs

O’Brien

Kenny

2019

Perspectives

View full text Add to dashboard Cite

A Reception Study of Machine Translated Subtitles for MOOCs Ke HuAs MOOCs (Massive Open Online Courses) grow rapidly around the world, the language barrier is becoming a serious issue. Removing this obstacle by creating translated subtitles is an indispensable part ofdeveloping MOOCs and improving accessibility.Given the large quantity of MOOCs availableworldwide and the considerable demand for them, machine translation (MT) appearsto offer an alternative or complementary translation solution, thus providingthe motivation for this research.

show abstract

“…Approximately 1600 in-house translators make the European Commissions' Directorate-General for Translation (DGT) probably the world's largest translation service: In 2016 alone, the DGT received 73,000 translation requests, produced 2.2 million pages, and outsourced more than 650,000 pages to freelancers ( [2], p. 43). With such a high workload, the recent paradigm shift from statistical to neural machine translations, and the strive to maintain extremely high-quality standards, the DGT is constantly adapting to new challenges, such as the creation of clear and consistent guidelines or Texts were taken from different English newspaper articles and translated using the statistical MT system Google Translate (English into Dutch).…”

Section: Background and Related Researchmentioning

confidence: 99%

“…For human translations, the workflow at the DGT generally foresees a revision by a second person, which has not changed since the arrival of integrated MT systems, which means that the post-edited segments in these translations are automatically reviewed by a second person. The whole DGT workflow complies with the requirements of various standards, e.g., the ISO standard for translation services [3] and the ISO standard for post-editing of machine translation [4].The topic of (machine) translation quality in general has been researched from many different angles, e.g., in publications dealing with translation quality at the European Institutions, see [5][6][7][8], or with translation quality management, particularly at the DGT, e.g., [2]. Furthermore, there are more specialized guidelines for every language department.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Translation Quality and Error Recognition in Professional Neural Machine Translation Post-Editing

Vardaro¹,

Schaeffer²,

Hansen‐Schirra³

2019

Informatics

View full text Add to dashboard Cite

This study aims to analyse how translation experts from the German department of the European Commission's Directorate-General for Translation (DGT) identify and correct different error categories in neural machine translated texts (NMT) and their post-edited versions (NMTPE). The term translation expert encompasses translator, post-editor as well as revisor. Even though we focus on neural machine-translated segments, translator and post-editor are used synonymously because of the combined workflow using CAT-Tools as well as machine translation. Only the distinction between post-editor, which refers to a DGT translation expert correcting the neural machine translation output, and revisor, which refers to a DGT translation expert correcting the post-edited version of the neural machine translation output, is important and made clear whenever relevant. Using an automatic error annotation tool and the more fine-grained manual error annotation framework to identify characteristic error categories in the DGT texts, a corpus analysis revealed that quality assurance measures by post-editors and revisors of the DGT are most often necessary for lexical errors. More specifically, the corpus analysis showed that, if post-editors correct mistranslations, terminology or stylistic errors in an NMT sentence, revisors are likely to correct the same error type in the same post-edited sentence, suggesting that the DGT experts were being primed by the NMT output. Subsequently, we designed a controlled eye-tracking and key-logging experiment to compare participants' eye movements for test sentences containing the three identified error categories (mistranslations, terminology or stylistic errors) and for control sentences without errors. We examined the three error types' effect on early (first fixation durations, first pass durations) and late eye movement measures (e.g., total reading time and regression path durations). Linear mixed-effects regression models predict what kind of behaviour of the DGT experts is associated with the correction of different error types during the post-editing process.Informatics 2019, 6, 41 2 of 29 the development of their own machine translation systems. Statistical machine translation (internally referred to as MT@EC) has been available at the DGT since 2013 and is now coming to an end. The new neural system, eTranslation, was launched in November 2017 and is able to "translate between any pair of the 24 official EU languages, as well as Icelandic and Norwegian (Bokmål): it can handle formatted documents and plain text; it translates multiple documents into multiple languages in "one go"; it accepts diverse input formats including XML and PDF; it retains formatting; and it provides specific output formats for computer-aided translation, i.e., TMX11 and XLIFF."It is trained with the aligned source and target segments that have been produced over the years-amounting to approximately 1.2 billion training segments ([1], p. 3).However, the usage of machine translation requires a different form of revisi...

show abstract

Translation Quality, Quality Management and Agency: Principles and Practice in the European Union Institutions

Cited by 10 publications

References 13 publications

Quantifying the Effect of Machine Translation in a High-Quality Human Translation Production Process

Quantifying the Effect of Machine Translation in a High-Quality Human Translation Production Process

A reception study of machine translated subtitles for MOOCs

Translation Quality and Error Recognition in Professional Neural Machine Translation Post-Editing

Contact Info

Product

Resources

About