diff --git a/spacy/pipeline/entity_linker.py b/spacy/pipeline/entity_linker.py
index 6fe322b62..63d5cccc2 100644
--- a/spacy/pipeline/entity_linker.py
+++ b/spacy/pipeline/entity_linker.py
@@ -27,9 +27,6 @@ ActivationsT = Dict[str, Union[List[Ragged], List[str]]]
KNOWLEDGE_BASE_IDS = "kb_ids"
-# See #9050
-BACKWARD_OVERWRITE = True
-
default_model_config = """
[model]
@architectures = "spacy.EntityLinker.v2"
@@ -60,7 +57,7 @@ DEFAULT_NEL_MODEL = Config().from_str(default_model_config)["model"]
"entity_vector_length": 64,
"get_candidates": {"@misc": "spacy.CandidateGenerator.v1"},
"get_candidates_batch": {"@misc": "spacy.CandidateBatchGenerator.v1"},
- "overwrite": True,
+ "overwrite": False,
"scorer": {"@scorers": "spacy.entity_linker_scorer.v1"},
"use_gold_ents": True,
"candidates_batch_size": 1,
@@ -191,7 +188,7 @@ class EntityLinker(TrainablePipe):
get_candidates_batch: Callable[
[KnowledgeBase, Iterable[Span]], Iterable[Iterable[Candidate]]
],
- overwrite: bool = BACKWARD_OVERWRITE,
+ overwrite: bool = False,
scorer: Optional[Callable] = entity_linker_score,
use_gold_ents: bool,
candidates_batch_size: int,
@@ -215,6 +212,7 @@ class EntityLinker(TrainablePipe):
Callable[[KnowledgeBase, Iterable[Span]], Iterable[Iterable[Candidate]]],
Iterable[Candidate]]
): Function that produces a list of candidates, given a certain knowledge base and several textual mentions.
+ overwrite (bool): Whether to overwrite existing non-empty annotations.
scorer (Optional[Callable]): The scoring method. Defaults to Scorer.score_links.
use_gold_ents (bool): Whether to copy entities from gold docs or not. If false, another
component must provide entity annotations.
diff --git a/spacy/pipeline/morphologizer.pyx b/spacy/pipeline/morphologizer.pyx
index 293add9e1..fabc51fee 100644
--- a/spacy/pipeline/morphologizer.pyx
+++ b/spacy/pipeline/morphologizer.pyx
@@ -21,10 +21,6 @@ from ..scorer import Scorer
from ..training import validate_examples, validate_get_examples
from ..util import registry
-# See #9050
-BACKWARD_OVERWRITE = True
-BACKWARD_EXTEND = False
-
default_model_config = """
[model]
@architectures = "spacy.Tagger.v2"
@@ -102,8 +98,8 @@ class Morphologizer(Tagger):
model: Model,
name: str = "morphologizer",
*,
- overwrite: bool = BACKWARD_OVERWRITE,
- extend: bool = BACKWARD_EXTEND,
+ overwrite: bool = False,
+ extend: bool = False,
scorer: Optional[Callable] = morphologizer_score,
save_activations: bool = False,
):
@@ -113,6 +109,8 @@ class Morphologizer(Tagger):
model (thinc.api.Model): The Thinc Model powering the pipeline component.
name (str): The component instance name, used to add entries to the
losses during training.
+ overwrite (bool): Whether to overwrite existing annotations.
+ extend (bool): Whether to extend existing annotations.
scorer (Optional[Callable]): The scoring method. Defaults to
Scorer.score_token_attr for the attributes "pos" and "morph" and
Scorer.score_token_attr_per_feat for the attribute "morph".
diff --git a/spacy/pipeline/sentencizer.pyx b/spacy/pipeline/sentencizer.pyx
index 77f4e8adb..6c2565170 100644
--- a/spacy/pipeline/sentencizer.pyx
+++ b/spacy/pipeline/sentencizer.pyx
@@ -10,9 +10,6 @@ from ..language import Language
from ..scorer import Scorer
from .. import util
-# see #9050
-BACKWARD_OVERWRITE = False
-
@Language.factory(
"sentencizer",
assigns=["token.is_sent_start", "doc.sents"],
@@ -52,13 +49,14 @@ class Sentencizer(Pipe):
name="sentencizer",
*,
punct_chars=None,
- overwrite=BACKWARD_OVERWRITE,
+ overwrite=False,
scorer=senter_score,
):
"""Initialize the sentencizer.
punct_chars (list): Punctuation characters to split on. Will be
serialized with the nlp object.
+ overwrite (bool): Whether to overwrite existing annotations.
scorer (Optional[Callable]): The scoring method. Defaults to
Scorer.score_spans for the attribute "sents".
diff --git a/spacy/pipeline/senter.pyx b/spacy/pipeline/senter.pyx
index 42feeb277..a7d263e94 100644
--- a/spacy/pipeline/senter.pyx
+++ b/spacy/pipeline/senter.pyx
@@ -18,8 +18,6 @@ from ..training import validate_examples, validate_get_examples
from ..util import registry
from .. import util
-# See #9050
-BACKWARD_OVERWRITE = False
default_model_config = """
[model]
@@ -83,7 +81,7 @@ class SentenceRecognizer(Tagger):
model,
name="senter",
*,
- overwrite=BACKWARD_OVERWRITE,
+ overwrite=False,
scorer=senter_score,
save_activations: bool = False,
):
@@ -93,6 +91,7 @@ class SentenceRecognizer(Tagger):
model (thinc.api.Model): The Thinc Model powering the pipeline component.
name (str): The component instance name, used to add entries to the
losses during training.
+ overwrite (bool): Whether to overwrite existing annotations.
scorer (Optional[Callable]): The scoring method. Defaults to
Scorer.score_spans for the attribute "sents".
save_activations (bool): save model activations in Doc when annotating.
diff --git a/spacy/pipeline/tagger.pyx b/spacy/pipeline/tagger.pyx
index a6be51c3c..101d8bcea 100644
--- a/spacy/pipeline/tagger.pyx
+++ b/spacy/pipeline/tagger.pyx
@@ -27,9 +27,6 @@ from .. import util
ActivationsT = Dict[str, Union[List[Floats2d], List[Ints1d]]]
-# See #9050
-BACKWARD_OVERWRITE = False
-
default_model_config = """
[model]
@architectures = "spacy.Tagger.v2"
@@ -99,7 +96,7 @@ class Tagger(TrainablePipe):
model,
name="tagger",
*,
- overwrite=BACKWARD_OVERWRITE,
+ overwrite=False,
scorer=tagger_score,
neg_prefix="!",
save_activations: bool = False,
@@ -110,6 +107,7 @@ class Tagger(TrainablePipe):
model (thinc.api.Model): The Thinc Model powering the pipeline component.
name (str): The component instance name, used to add entries to the
losses during training.
+ overwrite (bool): Whether to overwrite existing annotations.
scorer (Optional[Callable]): The scoring method. Defaults to
Scorer.score_token_attr for the attribute "tag".
save_activations (bool): save model activations in Doc when annotating.
diff --git a/website/docs/api/entitylinker.mdx b/website/docs/api/entitylinker.mdx
index 238b62a2e..12b2f6bef 100644
--- a/website/docs/api/entitylinker.mdx
+++ b/website/docs/api/entitylinker.mdx
@@ -63,7 +63,7 @@ architectures and their arguments and hyperparameters.
| `entity_vector_length` | Size of encoding vectors in the KB. Defaults to `64`. ~~int~~ |
| `use_gold_ents` | Whether to copy entities from the gold docs or not. Defaults to `True`. If `False`, entities must be set in the training data or by an annotating component in the pipeline. ~~int~~ |
| `get_candidates` | Function that generates plausible candidates for a given `Span` object. Defaults to [CandidateGenerator](/api/architectures#CandidateGenerator), a function looking up exact, case-dependent aliases in the KB. ~~Callable[[KnowledgeBase, Span], Iterable[Candidate]]~~ |
-| `overwrite` 3.2 | Whether existing annotation is overwritten. Defaults to `True`. ~~bool~~ |
+| `overwrite` 3.2 | Whether existing annotation is overwritten. Defaults to `False`. ~~bool~~ |
| `scorer` 3.2 | The scoring method. Defaults to [`Scorer.score_links`](/api/scorer#score_links). ~~Optional[Callable]~~ |
| `save_activations` 4.0 | Save activations in `Doc` when annotating. Saved activations are `"ents"` and `"scores"`. ~~Union[bool, list[str]]~~ |
| `threshold` 3.4 | Confidence threshold for entity predictions. The default of `None` implies that all predictions are accepted, otherwise those with a score beneath the treshold are discarded. If there are no predictions with scores above the threshold, the linked entity is `NIL`. ~~Optional[float]~~ |
diff --git a/website/docs/api/morphologizer.mdx b/website/docs/api/morphologizer.mdx
index 4660ec312..9514bc773 100644
--- a/website/docs/api/morphologizer.mdx
+++ b/website/docs/api/morphologizer.mdx
@@ -45,7 +45,7 @@ architectures and their arguments and hyperparameters.
| Setting | Description |
| ----------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `model` | The model to use. Defaults to [Tagger](/api/architectures#Tagger). ~~Model[List[Doc], List[Floats2d]]~~ |
-| `overwrite` 3.2 | Whether the values of existing features are overwritten. Defaults to `True`. ~~bool~~ |
+| `overwrite` 3.2 | Whether the values of existing features are overwritten. Defaults to `False`. ~~bool~~ |
| `extend` 3.2 | Whether existing feature types (whose values may or may not be overwritten depending on `overwrite`) are preserved. Defaults to `False`. ~~bool~~ |
| `scorer` 3.2 | The scoring method. Defaults to [`Scorer.score_token_attr`](/api/scorer#score_token_attr) for the attributes `"pos"` and `"morph"` and [`Scorer.score_token_attr_per_feat`](/api/scorer#score_token_attr_per_feat) for the attribute `"morph"`. ~~Optional[Callable]~~ |
| `save_activations` 4.0 | Save activations in `Doc` when annotating. Saved activations are `"probabilities"` and `"label_ids"`. ~~Union[bool, list[str]]~~ |