Apply a “token-to-vector” model and set its outputs in the Doc.tensor attribute. This is mostly useful to share a single subnetwork between multiple components, e.g. to have one embedding and CNN network shared between a DependencyParser, Tagger and EntityRecognizer.

In order to use the Tok2Vec predictions, subsequent components should use the Tok2VecListener layer as the tok2vec subnetwork of their model. This layer will read data from the doc.tensor attribute during prediction. During training, the Tok2Vec component will save its prediction and backprop callback for each batch, so that the subsequent components can backpropagate to the shared weights. This implementation is used because it allows us to avoid relying on object identity within the models to achieve the parameter sharing.

Config and implementation

The default config is defined by the pipeline component factory and describes how the component should be configured. You can override its settings via the config argument on nlp.add_pipe or in your config.cfg for training. See the model architectures documentation for details on the architectures and their arguments and hyperparameters.

explosion/spaCy/master/spacy/pipeline/tok2vec.py

Tok2Vec.__init__ method

Create a new pipeline instance. In your application, you would normally use a shortcut for this and instantiate the component using its string name and nlp.add_pipe.

Tok2Vec.__call__ method

Apply the pipe to one document and add context-sensitive embeddings to the Doc.tensor attribute, allowing them to be used as features by downstream components. The document is modified in place, and returned. This usually happens under the hood when the nlp object is called on a text and all pipeline components are applied to the Doc in order. Both __call__ and pipe delegate to the predict and set_annotations methods.

Tok2Vec.pipe method

Apply the pipe to a stream of documents. This usually happens under the hood when the nlp object is called on a text and all pipeline components are applied to the Doc in order. Both __call__ and pipe delegate to the predict and set_annotations methods.

Tok2Vec.initialize method

Initialize the component for training and return an Optimizer. get_examples should be a function that returns an iterable of Example objects. At least one example should be supplied. The data examples are used to initialize the model of the component and can either be the full training data or a representative sample. Initialization includes validating the network, inferring missing shapes and setting up the label scheme based on the data. This method is typically called by Language.initialize.

Tok2Vec.predict method

Apply the component’s model to a batch of Doc objects without modifying them.

Tok2Vec.set_annotations method

Modify a batch of Doc objects, using pre-computed scores.

Tok2Vec.update method

Learn from a batch of Example objects containing the predictions and gold-standard annotations, and update the component’s model. Delegates to predict.

Tok2Vec.create_optimizer method

Create an optimizer for the pipeline component.

Tok2Vec.use_params methodcontextmanager

Modify the pipe’s model to use the given parameter values. At the end of the context, the original parameters are restored.

Tok2Vec.to_disk method

Serialize the pipe to disk.

Tok2Vec.from_disk method

Load the pipe from disk. Modifies the object in place and returns it.

Tok2Vec.to_bytes method

Serialize the pipe to a bytestring.

Tok2Vec.from_bytes method

Load the pipe from a bytestring. Modifies the object in place and returns it.

Serialization fields

During serialization, spaCy will export several data fields used to restore different aspects of the object. If needed, you can exclude them from serialization by passing in the string names via the exclude argument.