mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 09:26:27 +03:00
Update language models and alpha support overview
This commit is contained in:
parent
708cd37a2e
commit
a44da8fb34
|
@ -19,21 +19,6 @@ p spaCy currently supports the following languages and capabilities:
|
||||||
each icon in [ "pro", "pro", "con", "pro", "pro", "pro", "pro", "con" ]
|
each icon in [ "pro", "pro", "con", "pro", "pro", "pro", "pro", "con" ]
|
||||||
+cell.u-text-center #[+procon(icon)]
|
+cell.u-text-center #[+procon(icon)]
|
||||||
|
|
||||||
+row
|
|
||||||
+cell Chinese #[code zh]
|
|
||||||
each icon in [ "pro", "con", "con", "con", "con", "con", "con", "con" ]
|
|
||||||
+cell.u-text-center #[+procon(icon)]
|
|
||||||
|
|
||||||
+row
|
|
||||||
+cell Spanish #[code es]
|
|
||||||
each icon in [ "pro", "con", "con", "con", "con", "con", "con", "con" ]
|
|
||||||
+cell.u-text-center #[+procon(icon)]
|
|
||||||
|
|
||||||
p
|
|
||||||
| Chinese tokenization requires the
|
|
||||||
| #[+a("https://github.com/fxsjy/jieba") Jieba] library. Statistical
|
|
||||||
| models are coming soon.
|
|
||||||
|
|
||||||
|
|
||||||
+h(2, "alpha-support") Alpha support
|
+h(2, "alpha-support") Alpha support
|
||||||
|
|
||||||
|
@ -42,8 +27,13 @@ p
|
||||||
| the existing language data and extending the tokenization patterns.
|
| the existing language data and extending the tokenization patterns.
|
||||||
|
|
||||||
+table([ "Language", "Source" ])
|
+table([ "Language", "Source" ])
|
||||||
each language, code in { it: "Italian", fr: "French", pt: "Portuguese", nl: "Dutch", sv: "Swedish", hu: "Hungarian" }
|
each language, code in { zh: "Chinese", es: "Spanish", it: "Italian", fr: "French", pt: "Portuguese", nl: "Dutch", sv: "Swedish", fi: "Finnish", hu: "Hungarian" }
|
||||||
+row
|
+row
|
||||||
+cell #{language} #[code=code]
|
+cell #{language} #[code=code]
|
||||||
+cell
|
+cell
|
||||||
+src(gh("spaCy", "spacy/" + code)) spacy/#{code}
|
+src(gh("spaCy", "spacy/" + code)) spacy/#{code}
|
||||||
|
|
||||||
|
p
|
||||||
|
| Chinese tokenization requires the
|
||||||
|
| #[+a("https://github.com/fxsjy/jieba") Jieba] library. Statistical
|
||||||
|
| models are coming soon.
|
||||||
|
|
Loading…
Reference in New Issue
Block a user