The freedom of choice
Depending on your preferences, IT policy and data protection agreements, Globalese can be operated as a cloud-based solution or as an in-house system.
The Globalese API allows you to easily integrate and automate the different steps of the translation workflow, such as:
- creating projects and associating them with engines in Globalese
- triggering the machine translation of files from your CAT tool
- retrieving machine-translated files
Advanced tag handling
Tags and formatting in translation documents are retained by Globalese automatically. This means that you save time in the post-editing phase as the post-editors do not have to put additional effort into replacing deleted tags: Globalese is smart enough to do this job for you.
Automatic resource cleanup and normalization
All the resources uploaded to Globalese undergo a thorough technical cleanup, leaving only language- and content-related tasks to the resource managers.
When uploading a corpus, inline and formatting tags are stripped from the text and special characters are normalized.
When training an engine, the content of the corpora is filtered according to various criteria: whether the source text is the same as the target text, whether there is a length mismatch, and so on.
Groups help separate what needs to be separated, to build engines containing only relevant corpora for any given project. For each group a user belongs to, administrators can set permissions to manage or access corpora, engines and projects.
An engine can be used even during retraining. As soon as retraining finishes, Globalese automatically switches to the new version of the engine.