Are you in the position of preparing huge volumes of content for new language markets on a tight schedule? Stressed global content manager, meet Machine Translation (MT).
Q: What is Machine Translation?
A: Machine Translation (MT) is a computer-generated attempt to pair content in one language with existing translations in another. While MT lacks the nuanced comprehensive powers of the human brain, it can use sophisticated software to chew through large amounts of content in translation.
Q: Is MT the right solution for my project?
A: Here are seven quick questions concerning your content that will help you assess if MT may be right for your project:
If you’re in the blue with most of your responses, keep on reading. MT may be a good translation solution.
Q: How do I stand to benefit from using MT?
A: Does your boss like to save time and money? While a human translator may successfully translate up to 2,000 to 3,000 words per day with a high accuracy rate, a machine-translation process with human post-editing can more than double productivity while achieving near quality.
Q: Sounds great. Why haven’t we submitted to our robot overlords yet?
A: With speed comes some compromise. Machine translation can introduce inaccurate meanings, redundancies, awkward sentence structures and, at times, unintentionally funny mistakes.
Some mistakes are not so funny — especially in mission-critical healthcare and consumer safety scenarios — when a mistranslated sentence could mean life or death.
Q: How do I balance benefits of machine translation against the pitfalls?
A: A human/machine compromise (or hybrid solution) is the answer. Machine translation with “pre- and post-editing” is a methodology in which a linguist “trains” or programs the machine translation engine to correctly translate context-specific terminology, phrases with double meanings and case-based client exceptions to rules where the MT platform may have otherwise made a mistake (pre-editing). Following this, a human linguist reviews the output and smooths out the result according to the level of quality needed (post-editing).
Q: How do I prepare MT-friendly content?
A: MT works best on short, simple, grammatically-accurate sentences. Removing synonyms and flowery language will make the translation process smoother. Over the long term, train your technical writers to keep their sentences short and direct.
May we take you to our leader? For a more robust discussion about machine translation, be sure to check out our full newsletter article “Using Machine Translation to Your Advantage.” No matter what your goals are, we maintain a robust localization process to help define the best process for your needs.
