Commit
·
c86b489
1
Parent(s):
259d6b0
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,42 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: cc-by-sa-4.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
tags:
|
| 3 |
+
- spacy
|
| 4 |
+
- floret
|
| 5 |
+
- fasttext
|
| 6 |
+
- feature-extraction
|
| 7 |
+
- token-classification
|
| 8 |
+
language:
|
| 9 |
+
- tr
|
| 10 |
license: cc-by-sa-4.0
|
| 11 |
+
model-index:
|
| 12 |
+
- name: tr_vectors_web_md
|
| 13 |
+
results:
|
| 14 |
+
- task:
|
| 15 |
+
name: NMT
|
| 16 |
+
type: token-classification
|
| 17 |
+
metrics:
|
| 18 |
+
- name: Accuracy
|
| 19 |
+
type: accuracy
|
| 20 |
+
value: 0.1112
|
| 21 |
+
|
| 22 |
---
|
| 23 |
+
Medium sized Turkish Floret word vectors for spaCy.
|
| 24 |
+
|
| 25 |
+
The vectors are trained on MC4 corpus using Floret with the follwing hyperparameters:
|
| 26 |
+
|
| 27 |
+
```
|
| 28 |
+
floret cbow -dim 300 --mode floret --bucket 50000 -minn 4 -maxn5 -minCount 100
|
| 29 |
+
-neg 10 -hashCount 2 -thread 12 -epoch 5
|
| 30 |
+
```
|
| 31 |
+
|
| 32 |
+
Vector are published in Floret format.
|
| 33 |
+
|
| 34 |
+
| Feature | Description |
|
| 35 |
+
| --- | --- |
|
| 36 |
+
| **Name** | `tr_vectors_web_md` |
|
| 37 |
+
| **Version** | `1.0` |
|
| 38 |
+
| **Vectors** | 50000 keys (300 dimensions) |
|
| 39 |
+
| **Sources** | [MC4](https://arxiv.org/abs/1910.10683) |
|
| 40 |
+
| **License** | `cc-by-sa-4.0` |
|
| 41 |
+
| **Author** | [Duygu Altinok](https://www.onlyduygu.com/) |
|
| 42 |
+
|