mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 20:28:20 +03:00
36514b5762
<!--- Provide a general summary of your changes in the title. --> ## Description <!--- Use this section to describe your changes. If your changes required testing, include information about the testing environment and the tests you ran. If your test fixes a bug reported in an issue, don't forget to include the issue number. If your PR is still a work in progress, that's totally fine – just include a note to let us know. --> Add a rule-based French Lemmatizer following the english one and the excellent PR for [greek language optimizations](https://github.com/explosion/spaCy/pull/2558) to adapt the Lemmatizer class. ### Types of change <!-- What type of change does your PR cover? Is it a bug fix, an enhancement or new feature, or a change to the documentation? --> - Lemma dictionary used can be found [here](http://infolingu.univ-mlv.fr/DonneesLinguistiques/Dictionnaires/telechargement.html), I used the XML version. - Add several files containing exhaustive list of words for each part of speech - Add some lemma rules - Add POS that are not checked in the standard Lemmatizer, i.e PRON, DET, ADV and AUX - Modify the Lemmatizer class to check in lookup table as a last resort if POS not mentionned - Modify the lemmatize function to check in lookup table as a last resort - Init files are updated so the model can support all the functionalities mentioned above - Add words to tokenizer_exceptions_list.py in respect to regex used in tokenizer_exceptions.py ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [X] I have submitted the spaCy Contributor Agreement. - [X] I ran the tests, and all new and existing tests passed. - [X] My changes don't require a change to the documentation, or if they do, I've added all required information.
40 lines
1.1 KiB
Python
40 lines
1.1 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
PRONOUNS_IRREG = {
|
|
"aucune": ("aucun",),
|
|
"celle-ci": ("celui-ci",),
|
|
"celles-ci": ("celui-ci",),
|
|
"ceux-ci": ("celui-ci",),
|
|
"celle-là": ("celui-là",),
|
|
"celles-là": ("celui-là",),
|
|
"ceux-là": ("celui-là",),
|
|
"celle": ("celui",),
|
|
"celles": ("celui",),
|
|
"ceux": ("celui",),
|
|
"certaines": ("certains",),
|
|
"chacune": ("chacun",),
|
|
"icelle": ("icelui",),
|
|
"icelles": ("icelui",),
|
|
"iceux": ("icelui",),
|
|
"la": ("le",),
|
|
"les": ("le",),
|
|
"laquelle": ("lequel",),
|
|
"lesquelles": ("lequel",),
|
|
"lesquels": ("lequel",),
|
|
"elle-même": ("lui-même",),
|
|
"elles-mêmes": ("lui-même",),
|
|
"eux-mêmes": ("lui-même",),
|
|
"quelle": ("quel",),
|
|
"quelles": ("quel",),
|
|
"quels": ("quel",),
|
|
"quelques-unes": ("quelqu'un",),
|
|
"quelques-uns": ("quelqu'un",),
|
|
"quelque-une": ("quelqu'un",),
|
|
"qu": ("que",),
|
|
"telle": ("tel",),
|
|
"telles": ("tel",),
|
|
"tels": ("tel",),
|
|
"toutes": ("tous",),
|
|
} |