Examining the general impact of the Controlled Languages rules in the context of Machine Translation has been an area of research for many years. The present study focuses on the following question: How do the Controlled Language (CL) rules impact the Machine Translation (MT) output individually? Analyzing a German corpus-based test suite of technical texts that have been translated into English by different MT systems, the study endeavors to answer this question at different levels: the general impact of CL rules (rule- and system-independent), their impact at rule level (system-independent), their impact at system level (rule-independent), and at rule and system level. The results of five MT systems (a rule-based system, a statistical system, two differently constructed hybrid systems, and a neural system) are analyzed and contrasted. For this, a mixed-methods triangulation approach that includes error annotation, human evaluation, and automatic evaluation was applied. The data were analyzed both qualitatively and quantitatively based on the following parameters: number and type of MT errors, style and content quality, and scores from two automatic evaluation metrics. In line with many studies, the results show a general positive impact of the applied CL rules on the MT output. However, at rule level, only four rules proved to have positive effects on all parameters; three rules had negative effects on the parameters; and two rules did not show any significant impact. At rule and system level, the rules affected the MT systems differently, as expected. Some rules that had a positive impact on earlier MT approaches did not show the same impact on the neural MT approach. Furthermore, the neural MT delivered distinctly better results than earlier MT approaches, namely the highest error-free, style and content quality rates both before and after the rules application, which indicates that the neural
Aktualisiert: 2023-06-16
> findR *
Examining the general impact of the Controlled Languages rules in the context of Machine Translation has been an area of research for many years. The present study focuses on the following question: How do the Controlled Language (CL) rules impact the Machine Translation (MT) output individually? Analyzing a German corpus-based test suite of technical texts that have been translated into English by different MT systems, the study endeavors to answer this question at different levels: the general impact of CL rules (rule- and system-independent), their impact at rule level (system-independent), their impact at system level (rule-independent), and at rule and system level. The results of five MT systems (a rule-based system, a statistical system, two differently constructed hybrid systems, and a neural system) are analyzed and contrasted. For this, a mixed-methods triangulation approach that includes error annotation, human evaluation, and automatic evaluation was applied. The data were analyzed both qualitatively and quantitatively based on the following parameters: number and type of MT errors, style and content quality, and scores from two automatic evaluation metrics. In line with many studies, the results show a general positive impact of the applied CL rules on the MT output. However, at rule level, only four rules proved to have positive effects on all parameters; three rules had negative effects on the parameters; and two rules did not show any significant impact. At rule and system level, the rules affected the MT systems differently, as expected. Some rules that had a positive impact on earlier MT approaches did not show the same impact on the neural MT approach. Furthermore, the neural MT delivered distinctly better results than earlier MT approaches, namely the highest error-free, style and content quality rates both before and after the rules application, which indicates that the neural
Aktualisiert: 2023-04-06
> findR *
MEHR ANZEIGEN
Bücher von Marzouk, Shaimaa
Sie suchen ein Buch oder Publikation vonMarzouk, Shaimaa ? Bei Buch findr finden Sie alle Bücher Marzouk, Shaimaa.
Entdecken Sie neue Bücher oder Klassiker für Sie selbst oder zum Verschenken. Buch findr hat zahlreiche Bücher
von Marzouk, Shaimaa im Sortiment. Nehmen Sie sich Zeit zum Stöbern und finden Sie das passende Buch oder die
Publiketion für Ihr Lesevergnügen oder Ihr Interessensgebiet. Stöbern Sie durch unser Angebot und finden Sie aus
unserer großen Auswahl das Buch, das Ihnen zusagt. Bei Buch findr finden Sie Romane, Ratgeber, wissenschaftliche und
populärwissenschaftliche Bücher uvm. Bestellen Sie Ihr Buch zu Ihrem Thema einfach online und lassen Sie es sich
bequem nach Hause schicken. Wir wünschen Ihnen schöne und entspannte Lesemomente mit Ihrem Buch
von Marzouk, Shaimaa .
Marzouk, Shaimaa - Große Auswahl an Publikationen bei Buch findr
Bei uns finden Sie Bücher aller beliebter Autoren, Neuerscheinungen, Bestseller genauso wie alte Schätze. Bücher
von Marzouk, Shaimaa die Ihre Fantasie anregen und Bücher, die Sie weiterbilden und Ihnen wissenschaftliche Fakten
vermitteln. Ganz nach Ihrem Geschmack ist das passende Buch für Sie dabei. Finden Sie eine große Auswahl Bücher
verschiedenster Genres, Verlage, Schlagworte Genre bei Buchfindr:
Unser Repertoire umfasst Bücher von
Sie haben viele Möglichkeiten bei Buch findr die passenden Bücher für Ihr Lesevergnügen zu entdecken. Nutzen Sie
unsere Suchfunktionen, um zu stöbern und für Sie interessante Bücher in den unterschiedlichen Genres und Kategorien
zu finden. Neben Büchern von Marzouk, Shaimaa und Büchern aus verschiedenen Kategorien finden Sie schnell und
einfach auch eine Auflistung thematisch passender Publikationen. Probieren Sie es aus, legen Sie jetzt los! Ihrem
Lesevergnügen steht nichts im Wege. Nutzen Sie die Vorteile Ihre Bücher online zu kaufen und bekommen Sie die
bestellten Bücher schnell und bequem zugestellt. Nehmen Sie sich die Zeit, online die Bücher Ihrer Wahl anzulesen,
Buchempfehlungen und Rezensionen zu studieren, Informationen zu Autoren zu lesen. Viel Spaß beim Lesen wünscht Ihnen
das Team von Buchfindr.