Training is the process by which a user teaches Re:infer what labels to apply to verbatims. A user trains Re:infer by manually reviewing verbatims and applying all the labels they think are relevant. Each time a user spends some time reviewing verbatims, it triggers a re-training event where Re:infer uses the newly reviewed verbatims to improve its understanding of the label concepts.

 

After each re-training event, the model re-reviews all of the unreviewed verbatims in the dataset and updates the predicted labels and associated sentiment scores (if sentiment analysis is enabled).


To understand how the model training process works in detail, see here.



Previous: Models     |     Next: Validation