Commit
•
9dfa995
1
Parent(s):
15320c5
Update README.md
Browse files
README.md
CHANGED
|
@@ -18,12 +18,12 @@ This is a FastText model for text classification, trained on my news dataset dat
|
|
| 18 |
|
| 19 |
This model uses FastText to classify text into 11 categories. It has been trained on ~70_000 examples and achieves an accuracy of 0.8691016964865116 on a test dataset.
|
| 20 |
|
| 21 |
-
|
| 22 |
|
| 23 |
The model is designed to classify any languages news articles into 11 categories, but was originally trained to categorize Russian-language news.
|
| 24 |
|
| 25 |
|
| 26 |
-
|
| 27 |
|
| 28 |
|
| 29 |
The news category is assigned by the classifier to one of 11 categories:
|
|
@@ -40,6 +40,12 @@ The news category is assigned by the classifier to one of 11 categories:
|
|
| 40 |
- travel (путешествия)
|
| 41 |
}
|
| 42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
## Usage
|
| 44 |
|
| 45 |
To use this model, you will need the `fasttext` and `transformers` libraries. Install them using pip:
|
|
|
|
| 18 |
|
| 19 |
This model uses FastText to classify text into 11 categories. It has been trained on ~70_000 examples and achieves an accuracy of 0.8691016964865116 on a test dataset.
|
| 20 |
|
| 21 |
+
## Task
|
| 22 |
|
| 23 |
The model is designed to classify any languages news articles into 11 categories, but was originally trained to categorize Russian-language news.
|
| 24 |
|
| 25 |
|
| 26 |
+
## Categories
|
| 27 |
|
| 28 |
|
| 29 |
The news category is assigned by the classifier to one of 11 categories:
|
|
|
|
| 40 |
- travel (путешествия)
|
| 41 |
}
|
| 42 |
|
| 43 |
+
|
| 44 |
+
## Intended uses & limitations
|
| 45 |
+
|
| 46 |
+
The "gloss" category is used to select yellow press, trashy and dubious news. The model can get confused in the classification of news categories politics, society and conflicts.
|
| 47 |
+
|
| 48 |
+
|
| 49 |
## Usage
|
| 50 |
|
| 51 |
To use this model, you will need the `fasttext` and `transformers` libraries. Install them using pip:
|