mirror of
https://github.com/explosion/spaCy.git
synced 2025-10-30 23:47:31 +03:00
e962784531
* Add Lemmatizer and simplify related components * Add `Lemmatizer` pipe with `lookup` and `rule` modes using the `Lookups` tables. * Reduce `Tagger` to a simple tagger that sets `Token.tag` (no pos or lemma) * Reduce `Morphology` to only keep track of morph tags (no tag map, lemmatizer, or morph rules) * Remove lemmatizer from `Vocab` * Adjust many many tests Differences: * No default lookup lemmas * No special treatment of TAG in `from_array` and similar required * Easier to modify labels in a `Tagger` * No extra strings added from morphology / tag map * Fix test * Initial fix for Lemmatizer config/serialization * Adjust init test to be more generic * Adjust init test to force empty Lookups * Add simple cache to rule-based lemmatizer * Convert language-specific lemmatizers Convert language-specific lemmatizers to component lemmatizers. Remove previous lemmatizer class. * Fix French and Polish lemmatizers * Remove outdated UPOS conversions * Update Russian lemmatizer init in tests * Add minimal init/run tests for custom lemmatizers * Add option to overwrite existing lemmas * Update mode setting, lookup loading, and caching * Make `mode` an immutable property * Only enforce strict `load_lookups` for known supported modes * Move caching into individual `_lemmatize` methods * Implement strict when lang is not found in lookups * Fix tables/lookups in make_lemmatizer * Reallow provided lookups and allow for stricter checks * Add lookups asset to all Lemmatizer pipe tests * Rename lookups in lemmatizer init test * Clean up merge * Refactor lookup table loading * Add helper from `load_lemmatizer_lookups` that loads required and optional lookups tables based on settings provided by a config. Additional slight refactor of lookups: * Add `Lookups.set_table` to set a table from a provided `Table` * Reorder class definitions to be able to specify type as `Table` * Move registry assets into test methods * Refactor lookups tables config Use class methods within `Lemmatizer` to provide the config for particular modes and to load the lookups from a config. * Add pipe and score to lemmatizer * Simplify Tagger.score * Add missing import * Clean up imports and auto-format * Remove unused kwarg * Tidy up and auto-format * Update docstrings for Lemmatizer Update docstrings for Lemmatizer. Additionally modify `is_base_form` API to take `Token` instead of individual features. * Update docstrings * Remove tag map values from Tagger.add_label * Update API docs * Fix relative link in Lemmatizer API docs
47 lines
1.2 KiB
Python
47 lines
1.2 KiB
Python
from typing import Optional
|
|
|
|
from thinc.api import Model
|
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .stop_words import STOP_WORDS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .syntax_iterators import SYNTAX_ITERATORS
|
|
from .punctuation import TOKENIZER_INFIXES
|
|
from .lemmatizer import EnglishLemmatizer
|
|
from ...language import Language
|
|
from ...lookups import Lookups
|
|
|
|
|
|
class EnglishDefaults(Language.Defaults):
|
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
|
infixes = TOKENIZER_INFIXES
|
|
lex_attr_getters = LEX_ATTRS
|
|
syntax_iterators = SYNTAX_ITERATORS
|
|
stop_words = STOP_WORDS
|
|
|
|
|
|
class English(Language):
|
|
lang = "en"
|
|
Defaults = EnglishDefaults
|
|
|
|
|
|
@English.factory(
|
|
"lemmatizer",
|
|
assigns=["token.lemma"],
|
|
default_config={"model": None, "mode": "rule", "lookups": None},
|
|
scores=["lemma_acc"],
|
|
default_score_weights={"lemma_acc": 1.0},
|
|
)
|
|
def make_lemmatizer(
|
|
nlp: Language,
|
|
model: Optional[Model],
|
|
name: str,
|
|
mode: str,
|
|
lookups: Optional[Lookups],
|
|
):
|
|
lookups = EnglishLemmatizer.load_lookups(nlp.lang, mode, lookups)
|
|
return EnglishLemmatizer(nlp.vocab, model, name, mode=mode, lookups=lookups)
|
|
|
|
|
|
__all__ = ["English"]
|