mirror of
https://github.com/explosion/spaCy.git
synced 2025-07-10 00:02:19 +03:00
Add spancat_exclusive to pipeline
This commit is contained in:
parent
527a1818e5
commit
3d07c05cba
|
@ -13,6 +13,7 @@ from .sentencizer import Sentencizer
|
|||
from .tagger import Tagger
|
||||
from .textcat import TextCategorizer
|
||||
from .spancat import SpanCategorizer
|
||||
from .spancat_exclusive import SpanCategorizerExclusive
|
||||
from .span_ruler import SpanRuler
|
||||
from .textcat_multilabel import MultiLabel_TextCategorizer
|
||||
from .tok2vec import Tok2Vec
|
||||
|
@ -31,6 +32,7 @@ __all__ = [
|
|||
"SentenceRecognizer",
|
||||
"Sentencizer",
|
||||
"SpanCategorizer",
|
||||
"SpanCategorizerExclusive",
|
||||
"SpanRuler",
|
||||
"Tagger",
|
||||
"TextCategorizer",
|
||||
|
|
|
@ -78,7 +78,7 @@ def make_spancat(
|
|||
model: Model[Tuple[List[Doc], Ragged], Floats2d],
|
||||
spans_key: str,
|
||||
scorer: Optional[Callable],
|
||||
negative_weight: Optional[float] = 1.0,
|
||||
negative_weight: float = 1.0,
|
||||
allow_overlap: Optional[bool] = True,
|
||||
) -> "SpanCategorizerExclusive":
|
||||
"""Create a SpanCategorizer component. The span categorizer consists of two
|
||||
|
@ -95,7 +95,7 @@ def make_spancat(
|
|||
spans_key (str): Key of the doc.spans dict to save the spans under. During
|
||||
initialization and training, the component will look for spans on the
|
||||
reference document under the same key.
|
||||
negative_weight (Optional[float]): Multiplier for the loss terms.
|
||||
negative_weight (float): Multiplier for the loss terms.
|
||||
Can be used to down weigh the negative samples if there are too many.
|
||||
allow_overlap (Optional[bool]): If True the data is assumed to
|
||||
contain overlapping spans.
|
||||
|
@ -133,7 +133,6 @@ class Ranges:
|
|||
return False
|
||||
|
||||
|
||||
# TODO: Documentation
|
||||
class SpanCategorizerExclusive(TrainablePipe):
|
||||
"""Pipeline component to label spans of text.
|
||||
|
||||
|
@ -148,7 +147,7 @@ class SpanCategorizerExclusive(TrainablePipe):
|
|||
name: str = "spancat_exclusive",
|
||||
*,
|
||||
spans_key: str = "spans",
|
||||
negative_weight: Optional[float],
|
||||
negative_weight: float = 1.0,
|
||||
scorer: Optional[Callable] = spancat_score,
|
||||
allow_overlap: Optional[bool] = True,
|
||||
) -> None:
|
||||
|
@ -161,7 +160,7 @@ class SpanCategorizerExclusive(TrainablePipe):
|
|||
During initialization and training, the component will look for
|
||||
spans on the reference document under the same key. Defaults to
|
||||
`"spans"`.
|
||||
negative_weight (Optional[float]): Multiplier for the loss terms.
|
||||
negative_weight (float): Multiplier for the loss terms.
|
||||
Can be used to down weigh the negative samples if there are too many.
|
||||
scorer (Optional[Callable]): The scoring method. Defaults to
|
||||
Scorer.score_spans for the Doc.spans[spans_key] with overlapping
|
||||
|
@ -394,13 +393,15 @@ class SpanCategorizerExclusive(TrainablePipe):
|
|||
) -> None:
|
||||
"""Initialize the pipe for training, using a representative set
|
||||
of data examples.
|
||||
|
||||
get_examples (Callable[[], Iterable[Example]]): Function that
|
||||
returns a representative sample of gold-standard Example objects.
|
||||
nlp (Optional[Language]): The current nlp object the component is part of.
|
||||
labels (Optional[List[str]]): The labels to add to the component, typically generated by the
|
||||
`init labels` command. If no labels are provided, the get_examples
|
||||
callback is used to extract the labels from the data.
|
||||
DOCS: https://spacy.io/api/spancategorizer#initialize
|
||||
|
||||
DOCS: https://spacy.io/api/spancategorizerexclusive#initialize
|
||||
"""
|
||||
subbatch: List[Example] = []
|
||||
if labels is not None:
|
||||
|
@ -419,9 +420,11 @@ class SpanCategorizerExclusive(TrainablePipe):
|
|||
# + 1 for the "no-label" category
|
||||
Y = self.model.ops.alloc2f(spans.dataXd.shape[0], self._n_labels)
|
||||
self.model.initialize(X=(docs, spans), Y=Y)
|
||||
# FIXME I think this branch is broken
|
||||
else:
|
||||
raise ValueError("Cannot initialize without examples.")
|
||||
# FIXME: Ideally we want to raise an error to avoid implicitly
|
||||
# raising it when initializing without examples. For now, we'll just
|
||||
# copy over what `spancat` did.
|
||||
self.model.initialize()
|
||||
|
||||
def _validate_categories(self, examples: Iterable[Example]):
|
||||
# TODO
|
||||
|
|
Loading…
Reference in New Issue
Block a user