mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-22 20:09:18 +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 * Fix French and Polish lemmatizers * Remove outdated UPOS conversions * Update Russian lemmatizer init in tests * Add minimal init/run tests for custom lemmatizers * Add option to overwrite existing lemmas *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
44 lines
1.5 KiB
Python
44 lines
1.5 KiB
Python
from typing import Optional
|
|
|
|
from ...pipeline import Lemmatizer
|
|
from ...tokens import Token
|
|
|
|
|
|
class EnglishLemmatizer(Lemmatizer):
|
|
"""English lemmatizer. Only overrides is_base_form.
|
|
"""
|
|
|
|
def is_base_form(self, token: Token) -> bool:
|
|
"""
|
|
Check whether we're dealing with an uninflected paradigm, so we can
|
|
avoid lemmatization entirely.
|
|
|
|
univ_pos (unicode / int): The token's universal part-of-speech tag.
|
|
morphology (dict): The token's morphological features following the
|
|
Universal Dependencies scheme.
|
|
"""
|
|
univ_pos = token.pos_.lower()
|
|
morphology = token.morph.to_dict()
|
|
if univ_pos == "noun" and morphology.get("Number") == "Sing":
|
|
return True
|
|
elif univ_pos == "verb" and morphology.get("VerbForm") == "Inf":
|
|
return True
|
|
# This maps 'VBP' to base form -- probably just need 'IS_BASE'
|
|
# morphology
|
|
elif univ_pos == "verb" and (
|
|
morphology.get("VerbForm") == "Fin"
|
|
and morphology.get("Tense") == "Pres"
|
|
and morphology.get("Number") is None
|
|
):
|
|
return True
|
|
elif univ_pos == "adj" and morphology.get("Degree") == "Pos":
|
|
return True
|
|
elif morphology.get("VerbForm") == "Inf":
|
|
return True
|
|
elif morphology.get("VerbForm") == "None":
|
|
return True
|
|
elif morphology.get("Degree") == "Pos":
|
|
return True
|
|
else:
|
|
return False
|