Analysis of Machine Translation Post-editing of IT Texts under the Guidance of TAUS Guidelines

Abstract

Machine Translation Post-Editing (MTPE) is essential for enhancing the accuracy and proficiency of machine-generated translations across diverse sectors, such as scientific, technical, and translation services industries. The Translation Automation User Society (TAUS) standards are used in this study to investigate the applicability of MTPE to IT texts. Even though neural machine translation (NMT) has made great strides and is now able to provide translations that are more accurate, these results frequently still need to be refined by humans in order to satisfy professional and industry standards. This thesis explains how TAUS principles, which address common problems such as terminology accuracy, fluency, and general readability, can maximize MTPE.