spaCy/spacy/lang/nb/__init__.py
Adriane Boyd f99d6d5e39
Refactor scoring methods to use registered functions (#8766)
* Add scorer option to components

Add an optional `scorer` parameter to all pipeline components. If a
scoring function is provided, it overrides the default scoring method
for that component.

* Add registered scorers for all components

* Add `scorers` registry
* Move all scoring methods outside of components as independent
  functions and register
* Use the registered scoring methods as defaults in configs and inits

Additional:

* The scoring methods no longer have access to the full component, so
  use settings from `cfg` as default scorer options to handle settings
  such as `labels`, `threshold`, and `positive_label`
* The `attribute_ruler` scoring method no longer has access to the
  patterns, so all scoring methods are called
* Bug fix: `spancat` scoring method is updated to set `allow_overlap` to
  score overlapping spans correctly

* Update Russian lemmatizer to use direct score method

* Check type of cfg in Pipe.score

* Fix check

* Update spacy/pipeline/sentencizer.pyx

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Remove validate_examples from scoring functions

* Use Pipe.labels instead of Pipe.cfg["labels"]

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
2021-08-10 15:13:39 +02:00

51 lines
1.3 KiB
Python

from typing import Optional, Callable
from thinc.api import Model
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_INFIXES
from .punctuation import TOKENIZER_SUFFIXES
from .stop_words import STOP_WORDS
from .syntax_iterators import SYNTAX_ITERATORS
from ...language import Language
from ...pipeline import Lemmatizer
class NorwegianDefaults(Language.Defaults):
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
prefixes = TOKENIZER_PREFIXES
infixes = TOKENIZER_INFIXES
suffixes = TOKENIZER_SUFFIXES
syntax_iterators = SYNTAX_ITERATORS
stop_words = STOP_WORDS
class Norwegian(Language):
lang = "nb"
Defaults = NorwegianDefaults
@Norwegian.factory(
"lemmatizer",
assigns=["token.lemma"],
default_config={
"model": None,
"mode": "rule",
"overwrite": False,
"scorer": {"@scorers": "spacy.lemmatizer_scorer.v1"},
},
default_score_weights={"lemma_acc": 1.0},
)
def make_lemmatizer(
nlp: Language,
model: Optional[Model],
name: str,
mode: str,
overwrite: bool,
scorer: Optional[Callable],
):
return Lemmatizer(
nlp.vocab, model, name, mode=mode, overwrite=overwrite, scorer=scorer
)
__all__ = ["Norwegian"]