Powered by OpenAIRE graph
Found an issue? Give us feedback
addClaim

Comparing an understanding of translation quality in translation studies and machine translation quality estimation

Authors: Schett, Marita;

Comparing an understanding of translation quality in translation studies and machine translation quality estimation

Abstract

Die Fortschritte im Feld der maschinellen Übersetzung der vergangenen Jahre führten zu einem Anstieg in der kommerziellen Nutzung computerbasierter Übersetzungswerkzeuge. Um die erwartbare Qualität eines maschinellen Übersetzungssystems im Vorhinein einschätzen zu können, wurden sogenannte Machine Translation Quality Estimation-Tools (MTQE-Tools) entwickelt. Da in die Entwicklung dieser Tools jedoch meist keine Übersetzer*innen oder Translationswissenschaftler*innen involviert sind, stellt sich die Frage, inwiefern Qualitätskriterien, die in der Translationswissenschaft als wichtig erachtet werden, in MTQE-Tools Berücksichtigung finden. Die vorliegende Masterarbeit beschäftigt sich daher mit den Qualitätskriterien, die im Aufbau der wichtigsten MTQE-Tools angesetzt wurden, und vergleicht diese mit den von der Translationswissenschaft angenommenen Kriterien. Dazu wird eine umfangreiche Literaturanalyse durchgeführt, deren Ergebnisse im Rahmen einer Vergleichsanalyse gegenübergestellt, verglichen und interpretiert werden. Die Ergebnisse zeigen, dass auf der textuellen Ebene ähnliche Kriterien zur Anwendung kommen, besonders auf der kontextuellen Ebene aber translationswissenschaftlich abgesicherte Elemente von Translationsqualität von den MTQE-Tools nicht berücksichtigt werden.

The improvements made in machine translation in the past decade have led to an increased commercial use of machine translation tools. In order to be able to give a prediction on how reliable a machine translation system is, quality estimation tools for machine translation (MTQE tools) have been developed. However, since usually no translators or translation scholars are involved in the creation of MTQE tools, the question comes up to what extent quality criteria prevailing in translation studies have been incorporated into those tools. This Master’s thesis takes a close look at the quality criteria that have been used in the creation of the most relevant quality estimation tools to date and compares them with the quality criteria that prevail in translation studies. For this purpose, an extensive literature review is conducted, and the results are compared and interpreted in a comparative analysis. The results show that whereas similar criteria are used at the textual level, extra-textual quality features prevalent in translation studies are not (yet) part of MTQE tools.

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Upload OA version
Are you the author of this publication? Upload your Open Access version to Zenodo!
It’s fast and easy, just two clicks!