From 3468d535ad2ae0074683600c8b1dadaad89ca1cb Mon Sep 17 00:00:00 2001 From: ines Date: Fri, 6 Oct 2017 21:39:06 +0200 Subject: [PATCH] Update model benchmarks --- .../_facts-figures/_benchmarks-models.jade | 26 +++++++++++++++++-- 1 file changed, 24 insertions(+), 2 deletions(-) diff --git a/website/usage/_facts-figures/_benchmarks-models.jade b/website/usage/_facts-figures/_benchmarks-models.jade index 208e7da48..d8f9713b2 100644 --- a/website/usage/_facts-figures/_benchmarks-models.jade +++ b/website/usage/_facts-figures/_benchmarks-models.jade @@ -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