The Muse as part of the immersive editor
Description: Muses can be accessed through the so-called immersive editing which encompasses Predictive Typing, AutoPick and Muses as part of Predictive Typing. Muses can be created in the Resource Console or in Project Home > Muses. Muses are local resources. Muses need to be trained and provide subsegment suggestions to you as you type in the translation grid. Muses collect single and multiword expressions in source and target content, identifies correlations between source and target, and suggests the target expressions as a suggestion in the predictive typing.
Train a muse with a corpus of a few thousand segments. Let's assume that the corpus has the source expression "term base" and the target expression "Termdatenbank" and no explicit indication that both expressions are corresponding to each other. The Muse now detects correlations between such expressions. When you use the trained Muse now in a project, it compares the source segment with the extracted source expression from the training, and it suggests the target expression in the predictive typing during translation.
How to use a Muse in a local project:
- Open a local project from the Dashboard. Go to Project Home > Muses. Create a Muse in clicking the Create/use new link.
- When you create a new Muse, the Train Muse dialog appears immediately after you created the Muse. You can use your local TMs or offline copies of your TMs as well as your corpora to train the Muse. You can also later retrain your Muse in clicking the Retrain link.
- Check the check box left to the name of the Muse you want to use in your project.
- Now open a document in your project, go to Translations > Predictive Typing and AutoPick. Here you can make some further customization. Muse results are shown via Predictive Typing. If you disable Predictive Typing, you get no suggestions from Muses.