mirror of https://github.com/explosion/spaCy.git
3.1 KiB
3.1 KiB
import { Help } from 'components/typography'; import Link from 'components/link'
| System | Parser | Tagger | NER | WPS CPU words per second on CPU, higher is better |
WPS GPU words per second on GPU, higher is better |
|---|---|---|---|---|---|
en_core_web_trf (spaCy v3) |
6k | ||||
en_core_web_lg (spaCy v3) |
|||||
en_core_web_lg (spaCy v2) |
91.9 | 97.2 | 85.9 | 10k | |
| Stanza (StanfordNLP)1 | n/a2 | n/a2 | 88.8 | 234 | 2k |
| Flair | - | 97.9 | 89.3 |
Accuracy and speed on the
OntoNotes 5.0 corpus.
**1. **
Qi et al. (2020). **2. ** Coming soon:
Qi et al. don't report parsing and tagging results on OntoNotes. We're working
on training Stanza on this corpus to allow direct comparison.
| System | POS | UAS | LAS |
|---|---|---|---|
| spaCy RoBERTa (2020) | |||
| spaCy CNN (2020) | |||
| Mrini et al. (2019) | 97.3 | 97.4 | 96.3 |
| Zhou and Zhao (2019) | 97.3 | 97.2 | 95.7 |
Accuracy on the Penn Treebank. See NLP-progress for more results.