explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-11-04 09:57:26 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update language overview and add section on 'xx' lang class

Browse Source
This commit is contained in:
ines 2017-05-28 01:15:44 +02:00
parent 84189c1cab
commit eb5a8be9ad
1 changed files with 38 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
website/docs/api/language-models.jade
View File

@ -2,7 +2,10 @@
include ../../_includes/_mixins include ../../_includes/_mixins
p spaCy currently supports the following languages and capabilities: p
| spaCy currently provides models for the following languages and
| capabilities:
+aside-code("Download language models", "bash"). +aside-code("Download language models", "bash").
python -m spacy download en python -m spacy download en
@ -22,12 +25,16 @@ p spaCy currently supports the following languages and capabilities:
+row +row
+cell French #[code fr] +cell French #[code fr]
each icon in [ "pro", "pro", "con", "pro", "con", "pro", "pro", "con" ] each icon in [ "pro", "con", "con", "pro", "con", "pro", "pro", "con" ]
+cell.u-text-center #[+procon(icon)] +cell.u-text-center #[+procon(icon)]
+h(2, "available") Available models +row
+cell Spanish #[code es]
each icon in [ "pro", "pro", "con", "pro", "pro", "pro", "pro", "con" ]
+cell.u-text-center #[+procon(icon)]
include ../usage/_models-list p
+button("/docs/usage/models", true, "primary") See available models
+h(2, "alpha-support") Alpha tokenization support +h(2, "alpha-support") Alpha tokenization support
@ -52,9 +59,35 @@ p
| #[+a("https://github.com/mocobeta/janome") Janome]. | #[+a("https://github.com/mocobeta/janome") Janome].
+table([ "Language", "Code", "Source" ]) +table([ "Language", "Code", "Source" ])
each language, code in { es: "Spanish", it: "Italian", pt: "Portuguese", nl: "Dutch", sv: "Swedish", fi: "Finnish", nb: "Norwegian Bokmål", da: "Danish", hu: "Hungarian", pl: "Polish", bn: "Bengali", he: "Hebrew", zh: "Chinese", ja: "Japanese" } each language, code in { it: "Italian", pt: "Portuguese", nl: "Dutch", sv: "Swedish", fi: "Finnish", nb: "Norwegian Bokmål", da: "Danish", hu: "Hungarian", pl: "Polish", bn: "Bengali", he: "Hebrew", zh: "Chinese", ja: "Japanese" }
+row +row
+cell #{language} +cell #{language}
+cell #[code=code] +cell #[code=code]
+cell +cell
+src(gh("spaCy", "spacy/lang/" + code)) lang/#{code} +src(gh("spaCy", "spacy/lang/" + code)) lang/#{code}
+h(2, "multi-language") Multi-language support
+tag-new(2)
p
| As of v2.0, spaCy supports models trained on more than one language. This
| is especially useful for named entity recognition. The language ID used
| for multi-language or language-neutral models is #[code xx]. The
| language class, a generic subclass containing only the base language data,
| can be found in #[+src(gh("spaCy", "spacy/lang/xx")) lang/xx].
p
| To load your model with the neutral, multi-language class, simply set
| #[code "language": "xx"] in your
| #[+a("/docs/usage/saving-loading#models-generating") model package]'s
| meta.json. You can also import the class directly, or call
| #[+api("util#get_lang_class") #[code util.get_lang_class()]] for
| lazy-loading.
+code("Standard import").
from spacy.lang.xx import MultiLanguage
nlp = MultiLanguage()
+code("With lazy-loading").
from spacy.util import get_lang_class
nlp = get_lang_class('xx')