Domain-adapting and evaluating machine translation for institutional German in South Tyrol

• Autores: Antonio Giovanni Contarino, Flavia De Camillis
• Localización: Corpus Use in Cross-linguistic Research: Paving the way for teaching, translation and professional communication / coord. por Marlén Izquierdo Fernández, Zuriñe Sanz Villar, 2023, ISBN 9789027214300, págs. 179-194
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • Building on a prior small-scale study on machine translation adaptation in the same language pair and domain (De Camillis 2021), this chapter reports on a (i) domain-adaptation, (ii) quality assessment, and (iii) automatic legal terminology evaluation experiment for legal South Tyrolean German. After collecting, sentence-aligning, and cleaning the LEXB parallel corpus, we used this bilingual resource to domain-adapt a ModernMT engine. Performance improvements were measured in terms of automatic quality metrics. The machine-translation of South Tyrolean legal terms was evaluated using an ad hoc automatic terminology evaluation tool. We observed a significant boost in performance and term accuracy in the output of the ModernMT adapted engine, but the improvement in legal terminology translation was deemed unsatisfactory.