The feature extractors that are available to train a text classifier using transfer learning.


enum MLTextClassifier.FeatureExtractorType


Selecting a Feature Extractor Type

case dynamicEmbedding

A feature extractor that provides embeddings for words, based on their in-context use.

case customEmbedding(URL)

A feature extractor that uses an embedding you provide, contained within a model file.

case staticEmbedding

A feature extractor that uses the standard, built-in word embeddings.

Describing a Feature Extractor Type

var description: String

A text representation of a feature extractor type.

var debugDescription: String

A text representation of the feature extractor type that’s suitable for output during debugging.

var playgroundDescription: Any

A description of the feature extractor type shown in a playground.

See Also

Selecting an Algorithm Type

case crf(revision: Int?)

A conditional random field model.

case maxEnt(revision: Int?)

A maximum entropy model.

Beta Software

This documentation contains preliminary information about an API or technology in development. This information is subject to change, and software implemented according to this documentation should be tested with final operating system software.

Learn more about using Apple's beta software