Skip to main content

Trainable Entities


Open In Collab Run in Postman

Train AutoNLP to learn patterns from your training examples and predict entities on its own. This is useful when the entity you want to extract does not have a finite list of values. E.g., Names of people, Addresses, Songs, Artists, etc.

In such a scenario just letting AutoNLP figure out what these entities are is the best way to go.

Prerequisites

Make sure to login using API and have your authorization token in a variable called AUTHORIZATION_TOKEN before running this API.

Create a Trainable Entity

While adding a training example if you do not specify anything for the entityType attribute it is considered as a trainable entity. In the example below

{
"intent": "play_song",
"text": "Play songs by John Lennon",
"type": "train",
"entities": [
{
"entity": "artist",
"value": "John Lennon",
"start": 14,
"end": 25,
"entityType": "trainable"
}
]
}

The entityType attribute defaults to trainable if it is not specified.