Start annotating manually, at least 5 or 10 annotations per label.
You may want to continue even after the first appearance of the blue “pop up“ announces that suggestions have been computed (see What is a suggestion?).
The system will observe what is happening and after a while start to train a first model using your annotation so far in order to calculate “suggestions”.
After a decent amount of annotations (at least 10 for the simplest scenario):
- Go to the Suggestions view
- The suggested category is presented in dotted line.
- Validate the suggested category by clicking on the chips or select the good one in the label list (manual annotation).
- Once the category has been accepted or corrected, you have to validate the document to enrich your dataset with this new document.
- Once the document validated, the system will propose you a new document with suggestion.
- You can filter (on the left) the list of suggestions on the labels you want to work on in particular!
- Sort suggestions according to their confidence level score.
- While browsing the suggestions and accepting / refusing them you will normally be able to proceed much quicker (generate more good examples & counter examples) than if you were to continue manually.
Let’s move on to the next step: