The training process is the step when the machine learns from the corpora. This can happen when you create a new engine, but you can also retrain your existing engines after certain milestones, for example when a project has finished. The process is similar to the continuous improvement of Translation Memories: with every segment added to your engine, it will produce better results.

To train an engine:

1. Upload corpora
Upload the corpora you want to build your engine from. These are typically TMX files, but you can also use TBX, CSV, TSV, or even translated CAT tool files with confirmed segments.

2. Create engine
Create a new engine and choose which corpora you want to include.

3. Train
Hit the Train button. When training finishes, the engine is ready for translation.

If the engine contains a distinction between core and auxiliary corpora, Globalese will use the core corpora as a reference when training the engine. The training process will use segment pairs from the auxiliary corpora that are from the same domain as the core corpora, and discard those that are not.

Training queue

Engines sent to training may or may not spend some time in the training queue if you are using Globalese in the cloud, depending on the number of engines already queued by other users.