Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,24 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
# [Lenta Word2Vec CBOW 300D]
|
| 5 |
+
|
| 6 |
+
## 🗃️ Corpus
|
| 7 |
+
109k+ words from lenta.ru (2025)
|
| 8 |
+
|
| 9 |
+
## ⚙️ Параметры
|
| 10 |
+
- Algorithm: Word2Vec CBOW
|
| 11 |
+
- Vector size: 300
|
| 12 |
+
- Window size: 10
|
| 13 |
+
- Min frequency: 10
|
| 14 |
+
|
| 15 |
+
## 📊 Metrics
|
| 16 |
+
- Word analogy accuracy: 42.86%
|
| 17 |
+
- Semantic similarity correlation: 0.18
|
| 18 |
+
- Vocabulary coverage: 28.76%
|
| 19 |
+
|
| 20 |
+
## 💻 Use case
|
| 21 |
+
```python
|
| 22 |
+
from gensim.models import Word2Vec
|
| 23 |
+
model = Word2Vec.load("lenta_w2v_cbow_300d.model")
|
| 24 |
+
similar = model.wv.most_similar("путин")
|