spaCy/website/docs/api/dependencyparser.md
2020-09-29 20:53:05 +02:00

24 KiB

title tag source teaser api_base_class api_string_name api_trainable
DependencyParser class spacy/pipeline/dep_parser.pyx Pipeline component for syntactic dependency parsing /api/pipe parser true

A transition-based dependency parser component. The dependency parser jointly learns sentence segmentation and labelled dependency parsing, and can optionally learn to merge tokens that had been over-segmented by the tokenizer. The parser uses a variant of the non-monotonic arc-eager transition-system described by Honnibal and Johnson (2014), with the addition of a "break" transition to perform the sentence segmentation. Nivre (2005)'s pseudo-projective dependency transformation is used to allow the parser to predict non-projective parses.

The parser is trained using an imitation learning objective. It follows the actions predicted by the current weights, and at each state, determines which actions are compatible with the optimal parse that could be reached from the current state. The weights are updated such that the scores assigned to the set of optimal actions is increased, while scores assigned to other actions are decreased. Note that more than one action may be optimal for a given state.

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.

Example

from spacy.pipeline.dep_parser import DEFAULT_PARSER_MODEL
config = {
   "moves": None,
   "update_with_oracle_cut_size": 100,
   "learn_tokens": False,
   "min_action_freq": 30,
   "model": DEFAULT_PARSER_MODEL,
}
nlp.add_pipe("parser", config=config)
Setting Description
moves A list of transition names. Inferred from the data if not provided. Defaults to None. Optional[List[str]]
update_with_oracle_cut_size During training, cut long sequences into shorter segments by creating intermediate states based on the gold-standard history. The model is not very sensitive to this parameter, so you usually won't need to change it. Defaults to 100. int
learn_tokens Whether to learn to merge subtokens that are split relative to the gold standard. Experimental. Defaults to False. bool
min_action_freq The minimum frequency of labelled actions to retain. Rarer labelled actions have their label backed-off to "dep". While this primarily affects the label accuracy, it can also affect the attachment structure, as the labels are used to represent the pseudo-projectivity transformation. Defaults to 30. int
model The Model powering the pipeline component. Defaults to TransitionBasedParser. Model[List[Doc], List[Floats2d]]
%%GITHUB_SPACY/spacy/pipeline/dep_parser.pyx

DependencyParser.__init__

Example

# Construction via add_pipe with default model
parser = nlp.add_pipe("parser")

# Construction via add_pipe with custom model
config = {"model": {"@architectures": "my_parser"}}
parser = nlp.add_pipe("parser", config=config)

# Construction from class
from spacy.pipeline import DependencyParser
parser = DependencyParser(nlp.vocab, model)

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.

Name Description
vocab The shared vocabulary. Vocab
model The Model powering the pipeline component. Model[List[Doc], List[Floats2d]]
name String name of the component instance. Used to add entries to the losses during training. str
moves A list of transition names. Inferred from the data if not provided. Optional[List[str]]
keyword-only
update_with_oracle_cut_size During training, cut long sequences into shorter segments by creating intermediate states based on the gold-standard history. The model is not very sensitive to this parameter, so you usually won't need to change it. 100 is a good default. int
learn_tokens Whether to learn to merge subtokens that are split relative to the gold standard. Experimental. bool
min_action_freq The minimum frequency of labelled actions to retain. Rarer labelled actions have their label backed-off to "dep". While this primarily affects the label accuracy, it can also affect the attachment structure, as the labels are used to represent the pseudo-projectivity transformation. int

DependencyParser.__call__

Apply the pipe to one document. 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.

Example

doc = nlp("This is a sentence.")
parser = nlp.add_pipe("parser")
# This usually happens under the hood
processed = parser(doc)
Name Description
doc The document to process. Doc
RETURNS The processed document. Doc

DependencyParser.pipe

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.

Example

parser = nlp.add_pipe("parser")
for doc in parser.pipe(docs, batch_size=50):
    pass
Name Description
docs A stream of documents. Iterable[Doc]
keyword-only
batch_size The number of documents to buffer. Defaults to 128. int
YIELDS The processed documents in order. Doc

DependencyParser.initialize

Initialize the component for training. get_examples should be a function that returns an iterable of Example objects. 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.

This method was previously called begin_training.

Example

parser = nlp.add_pipe("parser")
parser.initialize(lambda: [], nlp=nlp)
Name Description
get_examples Function that returns gold-standard annotations in the form of Example objects. Callable], Iterable[Example
keyword-only
nlp The current nlp object. Defaults to None. Optional[Language]

DependencyParser.predict

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

Example

parser = nlp.add_pipe("parser")
scores = parser.predict([doc1, doc2])
Name Description
docs The documents to predict. Iterable[Doc]
RETURNS A helper class for the parse state (internal). StateClass

DependencyParser.set_annotations

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

Example

parser = nlp.add_pipe("parser")
scores = parser.predict([doc1, doc2])
parser.set_annotations([doc1, doc2], scores)
Name Description
docs The documents to modify. Iterable[Doc]
scores The scores to set, produced by DependencyParser.predict. Returns an internal helper class for the parse state. List[StateClass]

DependencyParser.update

Learn from a batch of Example objects, updating the pipe's model. Delegates to predict and get_loss.

Example

parser = nlp.add_pipe("parser")
optimizer = nlp.initialize()
losses = parser.update(examples, sgd=optimizer)
Name Description
examples A batch of Example objects to learn from. Iterable[Example]
keyword-only
drop The dropout rate. float
set_annotations Whether or not to update the Example objects with the predictions, delegating to set_annotations. bool
sgd An optimizer. Will be created via create_optimizer if not set. Optional[Optimizer]
losses Optional record of the loss during training. Updated using the component name as the key. Optional[Dict[str, float]]
RETURNS The updated losses dictionary. Dict[str, float]

DependencyParser.get_loss

Find the loss and gradient of loss for the batch of documents and their predicted scores.

Example

parser = nlp.add_pipe("parser")
scores = parser.predict([eg.predicted for eg in examples])
loss, d_loss = parser.get_loss(examples, scores)
Name Description
examples The batch of examples. Iterable[Example]
scores Scores representing the model's predictions. StateClass
RETURNS The loss and the gradient, i.e. (loss, gradient). Tuple[float, float]

DependencyParser.score

Score a batch of examples.

Example

scores = parser.score(examples)
Name Description
examples The examples to score. Iterable[Example]
RETURNS The scores, produced by Scorer.score_spans and Scorer.score_deps. Dict[str, Union[float, Dict[str, float]]]

DependencyParser.create_optimizer

Create an Optimizer for the pipeline component.

Example

parser = nlp.add_pipe("parser")
optimizer = parser.create_optimizer()
Name Description
RETURNS The optimizer. Optimizer

DependencyParser.use_params

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

Example

parser = DependencyParser(nlp.vocab)
with parser.use_params(optimizer.averages):
    parser.to_disk("/best_model")
Name Description
params The parameter values to use in the model. dict

DependencyParser.add_label

Add a new label to the pipe. Note that you don't have to call this method if you provide a representative data sample to the initialize method. In this case, all labels found in the sample will be automatically added to the model, and the output dimension will be inferred automatically.

Example

parser = nlp.add_pipe("parser")
parser.add_label("MY_LABEL")
Name Description
label The label to add. str
RETURNS 0 if the label is already present, otherwise 1. int

DependencyParser.set_output

Change the output dimension of the component's model by calling the model's attribute resize_output. This is a function that takes the original model and the new output dimension nO, and changes the model in place. When resizing an already trained model, care should be taken to avoid the "catastrophic forgetting" problem.

Example

parser = nlp.add_pipe("parser")
parser.set_output(512)
Name Description
nO The new output dimension. int

DependencyParser.to_disk

Serialize the pipe to disk.

Example

parser = nlp.add_pipe("parser")
parser.to_disk("/path/to/parser")
Name Description
path A path to a directory, which will be created if it doesn't exist. Paths may be either strings or Path-like objects. Union[str, Path]
keyword-only
exclude String names of serialization fields to exclude. Iterable[str]

DependencyParser.from_disk

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

Example

parser = nlp.add_pipe("parser")
parser.from_disk("/path/to/parser")
Name Description
path A path to a directory. Paths may be either strings or Path-like objects. Union[str, Path]
keyword-only
exclude String names of serialization fields to exclude. Iterable[str]
RETURNS The modified DependencyParser object. DependencyParser

DependencyParser.to_bytes

Example

parser = nlp.add_pipe("parser")
parser_bytes = parser.to_bytes()

Serialize the pipe to a bytestring.

Name Description
keyword-only
exclude String names of serialization fields to exclude. Iterable[str]
RETURNS The serialized form of the DependencyParser object. bytes

DependencyParser.from_bytes

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

Example

parser_bytes = parser.to_bytes()
parser = nlp.add_pipe("parser")
parser.from_bytes(parser_bytes)
Name Description
bytes_data The data to load from. bytes
keyword-only
exclude String names of serialization fields to exclude. Iterable[str]
RETURNS The DependencyParser object. DependencyParser

DependencyParser.labels

The labels currently added to the component.

Example

parser.add_label("MY_LABEL")
assert "MY_LABEL" in parser.labels
Name Description
RETURNS The labels added to the component. Tuple[str, ...]

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.

Example

data = parser.to_disk("/path", exclude=["vocab"])
Name Description
vocab The shared Vocab.
cfg The config file. You usually don't want to exclude this.
model The binary model data. You usually don't want to exclude this.