Translation consistency is a feature designed to provide translators with informative hints regarding how the source words were previously translated. These hints show previous translations for individual words along with the number that indicates how many times each translation was used in the project.
As the feature’s name states, its main task is to improve the consistency of translations within the project. As a result, you get higher quality translations that will be used in your applications, websites, etc.
Translation consistency is handled by an experimental machine learning technology. As soon as you start translating your project, machine learning algorithms engage, and the system shows previous translations for the source words and how often they were used in the project. The previous translation lists are formed based on the translations with the highest priority (approved, most voted, or last added ones) within the project.
Hover over the source words underlined with the light dashed line to see the previous translations formed by the translation consistency feature. You can also search previous translations for specific source words using the Search TM tab.
Currently, translation consistency is available for the following source and target languages:
New languages are added regularly.