2017-10-03 15:26:20 +03:00
|
|
|
//- 💫 DOCS > USAGE > FACTS & FIGURES > BENCHMARKS > MODEL COMPARISON
|
|
|
|
|
|
|
|
|
|
p
|
|
|
|
|
| In this section, we provide benchmark accuracies for the pre-trained
|
|
|
|
|
| model pipelines we distribute with spaCy. Evaluations are conducted
|
|
|
|
|
| end-to-end from raw text, with no "gold standard" pre-processing, over
|
|
|
|
|
| text from a mix of genres where possible.
|
|
|
|
|
|
|
|
|
|
+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].
|
|
|
|
|
|
2017-10-06 22:39:06 +03:00
|
|
|
+h(4, "benchmarks-models-english") English
|
|
|
|
|
|
2017-10-03 15:26:20 +03:00
|
|
|
+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
|
|
|
|
|
each data in ["2.x", "neural"]
|
|
|
|
|
+cell.u-text-right=data
|
|
|
|
|
+cell.u-text-right 91.4
|
|
|
|
|
+cell.u-text-right 85.5
|
|
|
|
|
+cell.u-text-right 97.0
|
|
|
|
|
+cell.u-text-right 8.2k
|
|
|
|
|
+cell.u-text-right #[strong 36 MB]
|
|
|
|
|
|
|
|
|
|
+row
|
|
|
|
|
+cell #[+a("/models/en#en_core_web_lg") #[code en_core_web_lg]] 2.0.0a0
|
|
|
|
|
each data in ["2.x", "neural"]
|
|
|
|
|
+cell.u-text-right=data
|
|
|
|
|
+cell.u-text-right #[strong 91.9]
|
|
|
|
|
+cell.u-text-right #[strong 86.4]
|
|
|
|
|
+cell.u-text-right #[strong 97.2]
|
|
|
|
|
+cell.u-text-right #[em n/a]
|
|
|
|
|
+cell.u-text-right 667 MB
|
|
|
|
|
|
|
|
|
|
+row("divider")
|
|
|
|
|
+cell #[code en_core_web_sm] 1.2.0
|
|
|
|
|
each data in ["1.x", "linear", 86.6, 78.5, 96.6]
|
|
|
|
|
+cell.u-text-right=data
|
|
|
|
|
+cell.u-text-right #[strong 25.7k]
|
|
|
|
|
+cell.u-text-right 50 MB
|
|
|
|
|
|
|
|
|
|
+row
|
|
|
|
|
+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
|
2017-10-06 22:39:06 +03:00
|
|
|
|
|
|
|
|
+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
|
