explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-04-20 09:01:58 +03:00
Code Issues Packages Projects Releases Wiki Activity

add ressource 'presque' in universe.json

Browse Source
This commit is contained in:
thjbbvlt 2024-05-31 18:25:47 +02:00
parent 3fa464b8c7
commit cb1f9457b4
1 changed files with 17 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
website/meta/universe.json
View File

@ -4519,19 +4519,29 @@
"category": ["standalone"]
},
{
"id": "quelquhui",
"title": "quelquhui",
"slogan": "tokenizer for contemporary french",
"description": "A tokenizer for french that handles inword parentheses like in _(b)rouille_, inclusive language (won't split _relecteur.rice.s_,but will split _mais.maintenant_), hyphens (split _peut-on_, or _pouvons-vous_ but not _tubulu-pimpant_), apostrophes (split _j'arrive_ or _j'arrivons_, but not _aujourd'hui_ or _r'garder_), emoticons, text-emoji (_:happy:_), urls, mails, ...",
"github": "thjbdvlt/quelquhui",
"code_example": ["import spacy", "import quelquhui", "nlp = spacy.load('fr_core_news_lg')", "nlp.tokenizer = quelquhui.Toquenizer(nlp.vocab)"],
"id": "presque",
"title": "presque",
"slogan": "normalizer for contemporary french.",
"description": "normalizer for french with focus on online and informal communication, _peùUUUt-èTRE_ becomes _peut-être_, _voilaaaa_ becomes _voilà_. it also harmonizes inclusive language (the user can chose how): by default, _auteur-rice-s-x et relecteur.xrices_ becomes _auteur·ricexs et relecteur·ricexs_.",
"github": "thjbdvlt/presque",
"code_example": [
"import spacy",
"import presque",
"",
"@spacy.Language.factory('presque_normalizer')",
"def create_presque_normalizer(nlp, name='presque_normalizer'):",
"return presque.Normalizer(nlp=nlp)",
"",
"nlp = spacy.load('fr_core_news_lg')",
"nlp.add_pipe('presque_normalizer', first=True)"
],
"code_language": "python",
"author": "thjbdvlt",
"author_links": {
"github": "thjbdvlt"
},
"category": ["pipeline"],
"tags": ["tokenizer", "french"]
"tags": ["normalizer", "french"]
}
],