Classifier by examples Deprecated

---

Please note that the use of the classifier by examples has been deprecated since version 1.10.0. Learn more about migrating projects to CAILA.

Classifier by examples — a classifier based on the pre-trained semantic similarity detection function.

It allows to group users’ responses to previously marked data. In other words, you can specify a phrase or a set of phrases as a reference to be compared to a user request. The system will check these requests for semantic correspondence to the specified phrases. If the threshold for such correspondence is high enough, then the two phrases can be considered to belong to the same class and the bot will respond to them in the same way.

The main advantage of this method is that the example ranking function works similar to the pattern ranking function. Thus, patterns and prototype phrases can be used together.

Learn more about how to connect the classifier to a bot and use it