explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-11 17:56:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update model benchmarks

Browse Source
This commit is contained in:
ines 2017-10-06 21:39:06 +02:00
parent 96a4e79d13
commit 3468d535ad
1 changed files with 24 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
website/usage/_facts-figures/_benchmarks-models.jade
View File

@ -6,14 +6,14 @@ p
| end-to-end from raw text, with no "gold standard" pre-processing, over
| text from a mix of genres where possible.
+under-construction
+aside("Methodology")
| The evaluation was conducted on raw text with no gold standard
| information. The parser, tagger and entity recognizer were trained on the
| #[+a("https://www.gabormelli.com/RKB/OntoNotes_Corpus") OntoNotes 5]
| corpus, the word vectors on #[+a("http://commoncrawl.org") Common Crawl].
+h(4, "benchmarks-models-english") English
+table(["Model", "spaCy", "Type", "UAS", "NER F", "POS", "WPS", "Size"])
+row
+cell #[+a("/models/en#en_core_web_sm") #[code en_core_web_sm]] 2.0.0a5
@ -46,3 +46,25 @@ p
+cell #[code en_core_web_md] 1.2.1
each data in ["1.x", "linear", 90.6, 81.4, 96.7, "18.8k", "1 GB"]
+cell.u-text-right=data
+h(4, "benchmarks-models-spanish") Spanish
+table(["Model", "spaCy", "Type", "UAS", "NER F", "POS", "WPS", "Size"])
+row
+cell #[+a("/models/es#es_core_web_sm") #[code es_core_web_sm]] 2.0.0a0
+cell.u-text-right 2.x
+cell.u-text-right neural
+cell.u-text-right #[strong 90.1]
+cell.u-text-right 89.0
+cell.u-text-right #[strong 96.7]
+cell.u-text-right #[em n/a]
+cell.u-text-right #[strong 36 MB]
+row("divider")
+cell #[code es_core_web_md] 1.1.0
each data in ["1.x", "linear", 87.5]
+cell.u-text-right=data
+cell #[strong 94.2]
+cell #[strong 96.7]
+cell.u-text-right #[em n/a]
+cell.u-text-right 377 MB