spaCy/spacy/lang/fr/lemmatizer.py
Ines Montani 43b960c01b
Refactor pipeline components, config and language data (#5759)
* Update with WIP

* Update with WIP

* Update with pipeline serialization

* Update types and pipe factories

* Add deep merge, tidy up and add tests

* Fix pipe creation from config

* Don't validate default configs on load

* Update spacy/language.py

Co-authored-by: Ines Montani <ines@ines.io>

* Adjust factory/component meta error

* Clean up factory args and remove defaults

* Add test for failing empty dict defaults

* Update pipeline handling and methods

* provide KB as registry function instead of as object

* small change in test to make functionality more clear

* update example script for EL configuration

* Fix typo

* Simplify test

* Simplify test

* splitting pipes.pyx into separate files

* moving default configs to each component file

* fix batch_size type

* removing default values from component constructors where possible (TODO: test 4725)

* skip instead of xfail

* Add test for config -> nlp with multiple instances

* pipeline.pipes -> pipeline.pipe

* Tidy up, document, remove kwargs

* small cleanup/generalization for Tok2VecListener

* use DEFAULT_UPSTREAM field

* revert to avoid circular imports

* Fix tests

* Replace deprecated arg

* Make model dirs require config

* fix pickling of keyword-only arguments in constructor

* WIP: clean up and integrate full config

* Add helper to handle function args more reliably

Now also includes keyword-only args

* Fix config composition and serialization

* Improve config debugging and add visual diff

* Remove unused defaults and fix type

* Remove pipeline and factories from meta

* Update spacy/default_config.cfg

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

* Update spacy/default_config.cfg

* small UX edits

* avoid printing stack trace for debug CLI commands

* Add support for language-specific factories

* specify the section of the config which holds the model to debug

* WIP: add Language.from_config

* Update with language data refactor WIP

* Auto-format

* Add backwards-compat handling for Language.factories

* Update morphologizer.pyx

* Fix morphologizer

* Update and simplify lemmatizers

* Fix Japanese tests

* Port over tagger changes

* Fix Chinese and tests

* Update to latest Thinc

* WIP: xfail first Russian lemmatizer test

* Fix component-specific overrides

* fix nO for output layers in debug_model

* Fix default value

* Fix tests and don't pass objects in config

* Fix deep merging

* Fix lemma lookup data registry

Only load the lookups if an entry is available in the registry (and if spacy-lookups-data is installed)

* Add types

* Add Vocab.from_config

* Fix typo

* Fix tests

* Make config copying more elegant

* Fix pipe analysis

* Fix lemmatizers and is_base_form

* WIP: move language defaults to config

* Fix morphology type

* Fix vocab

* Remove comment

* Update to latest Thinc

* Add morph rules to config

* Tidy up

* Remove set_morphology option from tagger factory

* Hack use_gpu

* Move [pipeline] to top-level block and make [nlp.pipeline] list

Allows separating component blocks from component order – otherwise, ordering the config would mean a changed component order, which is bad. Also allows initial config to define more components and not use all of them

* Fix use_gpu and resume in CLI

* Auto-format

* Remove resume from config

* Fix formatting and error

* [pipeline] -> [components]

* Fix types

* Fix tagger test: requires set_morphology?

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
2020-07-22 13:42:59 +02:00

135 lines
4.7 KiB
Python

from typing import Optional, List, Dict
from ...lemmatizer import Lemmatizer
from ...symbols import POS, NOUN, VERB, ADJ, ADV, PRON, DET, AUX, PUNCT, ADP
from ...symbols import SCONJ, CCONJ
class FrenchLemmatizer(Lemmatizer):
"""
French language lemmatizer applies the default rule based lemmatization
procedure with some modifications for better French language support.
The parts of speech 'ADV', 'PRON', 'DET', 'ADP' and 'AUX' are added to use
the rule-based lemmatization. As a last resort, the lemmatizer checks in
the lookup table.
"""
def __call__(
self, string: str, univ_pos: str, morphology: Optional[dict] = None
) -> List[str]:
lookup_table = self.lookups.get_table("lemma_lookup", {})
if "lemma_rules" not in self.lookups:
return [lookup_table.get(string, string)]
if univ_pos in (NOUN, "NOUN", "noun"):
univ_pos = "noun"
elif univ_pos in (VERB, "VERB", "verb"):
univ_pos = "verb"
elif univ_pos in (ADJ, "ADJ", "adj"):
univ_pos = "adj"
elif univ_pos in (ADP, "ADP", "adp"):
univ_pos = "adp"
elif univ_pos in (ADV, "ADV", "adv"):
univ_pos = "adv"
elif univ_pos in (AUX, "AUX", "aux"):
univ_pos = "aux"
elif univ_pos in (CCONJ, "CCONJ", "cconj"):
univ_pos = "cconj"
elif univ_pos in (DET, "DET", "det"):
univ_pos = "det"
elif univ_pos in (PRON, "PRON", "pron"):
univ_pos = "pron"
elif univ_pos in (PUNCT, "PUNCT", "punct"):
univ_pos = "punct"
elif univ_pos in (SCONJ, "SCONJ", "sconj"):
univ_pos = "sconj"
else:
return [self.lookup(string)]
index_table = self.lookups.get_table("lemma_index", {})
exc_table = self.lookups.get_table("lemma_exc", {})
rules_table = self.lookups.get_table("lemma_rules", {})
lemmas = self.lemmatize(
string,
index_table.get(univ_pos, {}),
exc_table.get(univ_pos, {}),
rules_table.get(univ_pos, []),
)
return lemmas
def lookup(self, string: str, orth: Optional[int] = None) -> str:
lookup_table = self.lookups.get_table("lemma_lookup", {})
if orth is not None and orth in lookup_table:
return lookup_table[orth][0]
return string
def lemmatize(
self,
string: str,
index: Dict[str, List[str]],
exceptions: Dict[str, Dict[str, List[str]]],
rules: Dict[str, List[List[str]]],
) -> List[str]:
lookup_table = self.lookups.get_table("lemma_lookup", {})
string = string.lower()
forms = []
if string in index:
forms.append(string)
return forms
forms.extend(exceptions.get(string, []))
oov_forms = []
if not forms:
for old, new in rules:
if string.endswith(old):
form = string[: len(string) - len(old)] + new
if not form:
pass
elif form in index or not form.isalpha():
forms.append(form)
else:
oov_forms.append(form)
if not forms:
forms.extend(oov_forms)
if not forms and string in lookup_table.keys():
forms.append(lookup_table[string][0])
if not forms:
forms.append(string)
return list(set(forms))
def is_base_form(univ_pos: str, morphology: Optional[dict] = None) -> bool:
"""
Check whether we're dealing with an uninflected paradigm, so we can
avoid lemmatization entirely.
"""
morphology = {} if morphology is None else morphology
others = [
key
for key in morphology
if key not in (POS, "Number", "POS", "VerbForm", "Tense")
]
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
and not others
):
return True
elif univ_pos == "adj" and morphology.get("Degree") == "pos":
return True
elif "VerbForm=inf" in morphology:
return True
elif "VerbForm=none" in morphology:
return True
elif "Number=sing" in morphology:
return True
elif "Degree=pos" in morphology:
return True
else:
return False