Training

Post-Editing Machine Translation

Meet the demands of a changing market and future-proof your services

Over the last decade, post-editing has become a mainstream choice for enterprises wanting to provide their content in different languages to a global audience. The emergence of Neural Machine Translation technology has led to renewed focus on MT and post-editing. With the help of technology improvements and continuing commercial demand for post-editing this is an important opportunity for translators that will continue to grow. 

The translator profile is evolving in line with the new translation and technology requirements. One such requirement is the need to offer post-editing as part of a complete skills portfolio. The ongoing technology developments, in particular Neural MT, do not reduce the role of translators but change and enhance it, opening up new opportunities. Alignment with the new requirements will help to future-proof the role of translator and increase employability in a field that is and will remain deeply interlinked with translation technology.

Benefits of the Post-Editing Course

The SDL Post-Editing Certification has been developed for translators who are interested in adding post-editing to their skill-set. It is intended to provide translators with the tools and knowledge they need to become successful post-editors. Our aim is to share our experiences with MT and PE through the Post-Editing Certification course and embark on a journey of continuous learning and skill-set enhancement.

The scope of the Post-Editing Certification is to introduce the translator to the techniques and skills involved in post-editing machine-translated output. It provides a theoretical overview of Machine Translation and post-editing, together with best-practice recommendations and practical examples.

The course explains known MT behaviors and equips translators with core skills and strategies for effective post-editing. Armed with this knowledge, new post-editors are ready to experience post-editing first-hand, meeting the demands of a changing market and future-proofing their careers.

   

Course Details

Introduction

The Certification course explains the importance of post-editing and the impact technology has on the role of translators. Machine Translation is placed into the much larger context of Artificial Intelligence and increased automation in our daily lives. A brief history of MT is presented, both general and SDL specific. Following on from the historical overview, MT and post-editing are presented as part of the end-to-end localization process. We look at the impact MT developments have on the localization industry where they allow businesses to translate more content and reduce turnaround times. When implementing MT, it is important to manage both business expectations and translators’ needs. Content continues to evolve and it is important to understand when PE is a suitable alternative to translation.

MT Technologies

We then discuss different MT technologies, with a particular focus on Neural Machine Translation. SMT learns to translate by analyzing large volumes of previously translated content. An NMT system learns from observing correlations between the source and target text and modifies itself to increase the likelihood of correct translations. While SMT is still used in some workflows and is therefore covered in the Certification course, NMT is now the technology of choice at SDL. The course provides an insight into the process involved in creating and testing MT solutions.

Post-Editing

The next step in the process is post-editing the MT output. Post-editing means that a human translator is editing or revising text that has been translated by machine translation software. Post-editing replaces conventional translation for MT projects. It is a skill that translators develop with time and experience – there is a learning curve associated with PE. The market makes a distinction between light and full post-editing and both concepts are explained in the course materials. The course explains the post-editing phase in detail and includes guidance on how to post-edit effectively as well as common patterns and behaviors of MT output to watch out for during post-editing. Common NMT behaviors are explained in detail to prepare translators for working with NMT output.

The Certification guide describes how to add Machine Translation in SDL Trados Studio.

Finally, we discuss how the quality improvements associated with NMT expand the reach of the technology across content and language pairs and how MT gives rise to new and augmented translation profiles.

The appendices contain detailed information on automated MT evaluations as well as a variety of multilingual practical examples.

Certification Exam Details

The exam is accessed online and comprises 30 multiple choice questions based on the supporting materials. Students have 3 attempts to pass the exam and achieve certification status.

There is a total of 30 questions per exam with a pass mark of 20.

The time allocated for finishing the exam will be 30 minutes.

At the end of the course, successful participants will receive Certification status and will be eligible to use the logo on their personal communications, via download from their SDL My Account.

Purchase video based training