mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-29 19:36:31 +03:00
134 lines
3.1 KiB
Plaintext
134 lines
3.1 KiB
Plaintext
//- 💫 DOCS > API > ENTITYRECOGNIZER
|
|
|
|
include ../../_includes/_mixins
|
|
|
|
p Annotate named entities on #[code Doc] objects.
|
|
|
|
+h(2, "load") EntityRecognizer.load
|
|
+tag classmethod
|
|
|
|
p Load the statistical model from the supplied path.
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row
|
|
+cell #[code path]
|
|
+cell #[code Path]
|
|
+cell The path to load from.
|
|
|
|
+row
|
|
+cell #[code vocab]
|
|
+cell #[code Vocab]
|
|
+cell The vocabulary. Must be shared by the documents to be processed.
|
|
|
|
+row
|
|
+cell #[code require]
|
|
+cell bool
|
|
+cell Whether to raise an error if the files are not found.
|
|
|
|
+footrow
|
|
+cell return
|
|
+cell #[code EntityRecognizer]
|
|
+cell The newly constructed object.
|
|
|
|
+h(2, "init") EntityRecognizer.__init__
|
|
+tag method
|
|
|
|
p Create an #[code EntityRecognizer].
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row
|
|
+cell #[code vocab]
|
|
+cell #[code Vocab]
|
|
+cell The vocabulary. Must be shared with documents to be processed.
|
|
|
|
+row
|
|
+cell #[code model]
|
|
+cell #[thinc.linear.AveragedPerceptron]
|
|
+cell The statistical model.
|
|
|
|
+footrow
|
|
+cell return
|
|
+cell #[code EntityRecognizer]
|
|
+cell The newly constructed object.
|
|
|
|
+h(2, "call") EntityRecognizer.__call__
|
|
+tag method
|
|
|
|
p Apply the entity recognizer, setting the NER tags onto the #[code Doc] object.
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row
|
|
+cell #[code doc]
|
|
+cell #[code Doc]
|
|
+cell The document to be processed.
|
|
|
|
+footrow
|
|
+cell return
|
|
+cell #[code None]
|
|
+cell -
|
|
|
|
+h(2, "pipe") EntityRecognizer.pipe
|
|
+tag method
|
|
|
|
p Process a stream of documents.
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row
|
|
+cell #[code stream]
|
|
+cell -
|
|
+cell The sequence of documents to process.
|
|
|
|
+row
|
|
+cell #[code batch_size]
|
|
+cell int
|
|
+cell The number of documents to accumulate into a working set.
|
|
|
|
+row
|
|
+cell #[code n_threads]
|
|
+cell int
|
|
+cell
|
|
| The number of threads with which to work on the buffer in
|
|
| parallel.
|
|
|
|
+footrow
|
|
+cell yield
|
|
+cell #[code Doc]
|
|
+cell Documents, in order.
|
|
|
|
+h(2, "update") EntityRecognizer.update
|
|
+tag method
|
|
|
|
p Update the statistical model.
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row
|
|
+cell #[code doc]
|
|
+cell #[code Doc]
|
|
+cell The example document for the update.
|
|
|
|
+row
|
|
+cell #[code gold]
|
|
+cell #[code GoldParse]
|
|
+cell The gold-standard annotations, to calculate the loss.
|
|
|
|
+footrow
|
|
+cell return
|
|
+cell int
|
|
+cell The loss on this example.
|
|
|
|
+h(2, "step_through") EntityRecognizer.step_through
|
|
+tag method
|
|
|
|
p Set up a stepwise state, to introspect and control the transition sequence.
|
|
|
|
+table(["Name", "Type", "Description"])
|
|
+row
|
|
+cell #[code doc]
|
|
+cell #[code Doc]
|
|
+cell The document to step through.
|
|
|
|
+footrow
|
|
+cell return
|
|
+cell #[code StepwiseState]
|
|
+cell A state object, to step through the annotation process.
|