spaCy/spacy/lang/ga/__init__.py
Jim O’Regan 8fe525beb5
Add an Irish lemmatiser, based on BuNaMo (#9102)
* add tréis/théis

* remove previous contents, add demutate/unponc

* fmt off/on wrapping

* type hints

* IrishLemmatizer (sic)

* Use spacy-lookups-data>=1.0.3

* Minor bug fixes, refactoring for IrishLemmatizer

* Fix return type for ADP list lookups
* Fix and refactor lookup table lookups for missing/string/list
* Remove unused variables

* skip lookup of verbal substantives and adjectives; just demutate

* Fix morph checks API details

* Add types and format

* Move helper methods into lemmatizer

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
2021-09-30 14:18:47 +02:00

34 lines
810 B
Python

from typing import Optional
from thinc.api import Model
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .stop_words import STOP_WORDS
from ...language import Language
from .lemmatizer import IrishLemmatizer
class IrishDefaults(Language.Defaults):
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
stop_words = STOP_WORDS
class Irish(Language):
lang = "ga"
Defaults = IrishDefaults
@Irish.factory(
"lemmatizer",
assigns=["token.lemma"],
default_config={"model": None, "mode": "pos_lookup", "overwrite": False},
default_score_weights={"lemma_acc": 1.0},
)
def make_lemmatizer(
nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool
):
return IrishLemmatizer(nlp.vocab, model, name, mode=mode, overwrite=overwrite)
__all__ = ["Irish"]