AI in the crossbase translation process

Böblingen, 22.07.2022: The crossbase translation process determines the translation requirements in all necessary foreign languages and manages the translation jobs.

 

The established way: standardized text and translation workflows

Due to the text module management and the sophisticated text workflow, only missing or outdated translations are fed into the translation process, i.e. a minimum of texts. In addition, crossbase "remembers" which texts are currently being translated in order to be able to react to any changes to the original text.

For this purpose, crossbase has developed a tool in which different contexts can be selected for translation, e.g. websites, e-catalogs, structures, print publications, etc. So that translations will only come into play where there is a definite need for them.

Pre-translation with DeepL

For more than three years, DeepL has been directly integrated as a machine translation solution. Individual or combined texts can be machine translated at the touch of a button. In a second phase, the texts can be assigned to the target country for review. Editing is done easily and conveniently via the crossbase web interface.
 
The dilemma with machine translation is that customer-specific dictionaries often cannot be used. This leads to extensive correction loops, especially for companies that use very specialized terminologies. In addition, it is very tedious to correct the same terms over and over again. 
 

NEW: The integration of glossaries for DeepL

Starting with version 508, glossaries were integrated into the machine translation in crossbase. This allows users to specify source and target language glossaries through the crossbase translation tool. The technical terms are thus translated correctly and the effort for correction is significantly reduced.

NEW: Connection to Microsoft Translator

Microsoft Translator can additionally be used for cloud-based machine translation. This offers more languages, see https://azure.microsoft.com/en-us/services/cognitive-services/translator/. This Azure service is very secure, scalable and offers a dictionary feature as well.