Update README.md
Browse files
README.md
CHANGED
|
@@ -4,4 +4,54 @@ language:
|
|
| 4 |
library_name: spacy
|
| 5 |
metrics:
|
| 6 |
- accuracy
|
| 7 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
library_name: spacy
|
| 5 |
metrics:
|
| 6 |
- accuracy
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
Russian pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.
|
| 10 |
+
|
| 11 |
+
| Feature | Description |
|
| 12 |
+
| --- | --- |
|
| 13 |
+
| **Name** | `ru_custom_new_model` |
|
| 14 |
+
| **Version** | `0.0.1` |
|
| 15 |
+
| **spaCy** | `>=3.7.0,<3.8.0` |
|
| 16 |
+
| **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
|
| 17 |
+
| **Components** | `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |
|
| 18 |
+
| **Vectors** | 500002 keys, 500002 unique vectors (300 dimensions) |
|
| 19 |
+
| **Sources** | n/a |
|
| 20 |
+
| **License** | `MIT` |
|
| 21 |
+
| **Author** | [Dessan](https://explosion.ai) |
|
| 22 |
+
|
| 23 |
+
### Label Scheme
|
| 24 |
+
|
| 25 |
+
<details>
|
| 26 |
+
|
| 27 |
+
<summary>View label scheme (905 labels for 3 components)</summary>
|
| 28 |
+
|
| 29 |
+
| Component | Labels |
|
| 30 |
+
| --- | --- |
|
| 31 |
+
| **`morphologizer`** | `Case=Nom\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Animacy=Anim\|Case=Nom\|Gender=Masc\|Number=Plur\|POS=NOUN`, `Aspect=Perf\|Mood=Ind\|Number=Plur\|POS=VERB\|Tense=Pa>| **`parser`** | `ROOT`, `acl`, `acl:relcl`, `advcl`, `advmod`, `amod`, `appos`, `aux`, `aux:pass`, `case`, `cc`, `ccomp`, `compound`, `conj`, `cop`, `csubj`, `csubj:pass`, `dep`, `det`, >| **`ner`** | `BOMB`, `DATE`, `LOC`, `MONEY`, `ORG`, `PER`, `PRODUCT`, `VIRUS` |
|
| 32 |
+
|
| 33 |
+
</details>
|
| 34 |
+
|
| 35 |
+
### Accuracy
|
| 36 |
+
|
| 37 |
+
| Type | Score |
|
| 38 |
+
| --- | --- |
|
| 39 |
+
| `TOKEN_ACC` | 99.68 |
|
| 40 |
+
| `TOKEN_P` | 97.28 |
|
| 41 |
+
| `TOKEN_R` | 98.31 |
|
| 42 |
+
| `TOKEN_F` | 97.79 |
|
| 43 |
+
| `POS_ACC` | 98.93 |
|
| 44 |
+
| `MORPH_ACC` | 97.49 |
|
| 45 |
+
| `MORPH_MICRO_P` | 98.97 |
|
| 46 |
+
| `MORPH_MICRO_R` | 98.30 |
|
| 47 |
+
| `MORPH_MICRO_F` | 98.64 |
|
| 48 |
+
| `SENTS_P` | 99.87 |
|
| 49 |
+
| `SENTS_R` | 99.85 |
|
| 50 |
+
| `SENTS_F` | 99.86 |
|
| 51 |
+
| `DEP_UAS` | 96.22 |
|
| 52 |
+
| `DEP_LAS` | 95.12 |
|
| 53 |
+
| `TAG_ACC` | 98.93 |
|
| 54 |
+
| `LEMMA_ACC` | 0.00 |
|
| 55 |
+
| `ENTS_P` | 95.24 |
|
| 56 |
+
| `ENTS_R` | 95.35 |
|
| 57 |
+
| `ENTS_F` | 95.30 |
|