Trainable Entities
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 log in 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.