mirror of
https://github.com/explosion/spaCy.git
synced 2025-01-14 11:36:24 +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 * Fix French and Polish lemmatizers * Remove outdated UPOS conversions * Update Russian lemmatizer init in tests * Add minimal init/run tests for custom lemmatizers * Add option to overwrite existing lemmas *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
92 lines
3.5 KiB
Python
92 lines
3.5 KiB
Python
from typing import List, Dict
|
|
|
|
from ...pipeline import Lemmatizer
|
|
from ...tokens import Token
|
|
|
|
|
|
class PolishLemmatizer(Lemmatizer):
|
|
# This lemmatizer implements lookup lemmatization based on the Morfeusz
|
|
# dictionary (morfeusz.sgjp.pl/en) by Institute of Computer Science PAS.
|
|
# It utilizes some prefix based improvements for verb and adjectives
|
|
# lemmatization, as well as case-sensitive lemmatization for nouns.
|
|
|
|
@classmethod
|
|
def get_lookups_config(cls, mode: str) -> Dict:
|
|
if mode == "lookup":
|
|
return {
|
|
"required_tables": [
|
|
"lemma_lookup_adj",
|
|
"lemma_lookup_adp",
|
|
"lemma_lookup_adv",
|
|
"lemma_lookup_aux",
|
|
"lemma_lookup_noun",
|
|
"lemma_lookup_num",
|
|
"lemma_lookup_part",
|
|
"lemma_lookup_pron",
|
|
"lemma_lookup_verb",
|
|
]
|
|
}
|
|
else:
|
|
return super().get_lookups_config(mode)
|
|
|
|
def lookup_lemmatize(self, token: Token) -> List[str]:
|
|
string = token.text
|
|
univ_pos = token.pos_
|
|
morphology = token.morph.to_dict()
|
|
lookup_pos = univ_pos.lower()
|
|
if univ_pos == "PROPN":
|
|
lookup_pos = "noun"
|
|
lookup_table = self.lookups.get_table("lemma_lookup_" + lookup_pos, {})
|
|
if univ_pos == "NOUN":
|
|
return self.lemmatize_noun(string, morphology, lookup_table)
|
|
if univ_pos != "PROPN":
|
|
string = string.lower()
|
|
if univ_pos == "ADJ":
|
|
return self.lemmatize_adj(string, morphology, lookup_table)
|
|
elif univ_pos == "VERB":
|
|
return self.lemmatize_verb(string, morphology, lookup_table)
|
|
return [lookup_table.get(string, string.lower())]
|
|
|
|
def lemmatize_adj(
|
|
self, string: str, morphology: dict, lookup_table: Dict[str, str]
|
|
) -> List[str]:
|
|
# this method utilizes different procedures for adjectives
|
|
# with 'nie' and 'naj' prefixes
|
|
if string[:3] == "nie":
|
|
search_string = string[3:]
|
|
if search_string[:3] == "naj":
|
|
naj_search_string = search_string[3:]
|
|
if naj_search_string in lookup_table:
|
|
return [lookup_table[naj_search_string]]
|
|
if search_string in lookup_table:
|
|
return [lookup_table[search_string]]
|
|
if string[:3] == "naj":
|
|
naj_search_string = string[3:]
|
|
if naj_search_string in lookup_table:
|
|
return [lookup_table[naj_search_string]]
|
|
return [lookup_table.get(string, string)]
|
|
|
|
def lemmatize_verb(
|
|
self, string: str, morphology: dict, lookup_table: Dict[str, str]
|
|
) -> List[str]:
|
|
# this method utilizes a different procedure for verbs
|
|
# with 'nie' prefix
|
|
if string[:3] == "nie":
|
|
search_string = string[3:]
|
|
if search_string in lookup_table:
|
|
return [lookup_table[search_string]]
|
|
return [lookup_table.get(string, string)]
|
|
|
|
def lemmatize_noun(
|
|
self, string: str, morphology: dict, lookup_table: Dict[str, str]
|
|
) -> List[str]:
|
|
# this method is case-sensitive, in order to work
|
|
# for incorrectly tagged proper names
|
|
if string != string.lower():
|
|
if string.lower() in lookup_table:
|
|
return [lookup_table[string.lower()]]
|
|
elif string in lookup_table:
|
|
return [lookup_table[string]]
|
|
return [string.lower()]
|
|
return [lookup_table.get(string, string)]
|