Page History
| Excerpt | ||
|---|---|---|
The Intent stage does a semantic comparison of a provided sentence against possible intents (using TensorFlow or a Neural Network on the Python Bridge), ifthe recognizer already has. If the confidence value is in the threshold, it will create a tag holding the intent. This recognizer uses a frozen Universal Sentence Encoder TensorFlow model to encode (using sentence embedding vectors) a list of intents. Then tags sentences that match an intent given a specified threshold of accuracy with the intent from the list of possible intents.
|
Configuration
Parameter summary Intent to find within the list of possible intents. default None name Intent
Adding an Intent
Click on the button to open the "Add new " dialog
Parameter summary Intent to add to the list of possible intents. default None name Write intent here Parameter summary Confidence adjustment for this very intent. default 1 name Confidence Adjustment type double
Recalculate Vectors
Click on the 
button to refresh and recalculate all vectors.
General Settings
| Include Page | ||||
|---|---|---|---|---|
|
Overview
Content Tools