Create a Feedback Example

Adds a feedback example to the dataset associated with the specified model.

Request Parameters

Name

Type

Description

Available Version

document

string

Intent or sentiment string to add to the dataset.

2.0

expectedLabel

string

Correct label for the example. Must be a label that exists in the dataset.

2.0

modelId

string

ID of the model that misclassified the image. The feedback example is added to the dataset associated with this model.

2.0

name

string

N/A for intent and sentiment models.

2.0

If a model returns an incorrect prediction for some text, you can use that text to improve the model. To improve the model, add the misclassified text to the dataset and retrain it to update the model.

The misclassified text that you add to the dataset is known as feedback. Use this API to add misclassified text with the correct label to the dataset from which the model was created.

Keep the following points in mind when creating feedback examples.

  • You pass in a modelId parameter, but the example is added to the dataset from which the specified model was created.

  • Add a feedback example to only one label per call.

Response Body

Name

Type

Description

Available Version

createdAt

date

Date and time that the feedback example was created.

2.0

id

long

ID of the feedback example.

2.0

label

object

Contains information about the label that the feedback example is associated with.

2.0

location

string

Feedback text.

2.0

name

string

N/A for intent and sentiment models.

2.0

object

string

Object returned; in this case, example.

2.0

Label Response Body

Name

Type

Description

Available Version

datasetId

long

ID of the dataset to which the feedback example’s label belongs.

2.0

id

long

ID of the feedback example’s label.

2.0

name

string

Name of the feedback example’s label.

2.0

numExamples

int

Number of examples that have the label.

2.0

Language