Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,11 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
# Toxic post classification using DistilBert
|
| 5 |
-
Use a pretrained DistilBert to train a classifier on the Toxic Comment dataset https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge.
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
---
|
| 8 |
# Toxic post classification using DistilBert
|
| 9 |
+
Use a pretrained DistilBert to train a classifier on the Toxic Comment dataset https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge.
|
| 10 |
+
The goal is to classify whether a comment is toxic or not. Note that the labels from the original datasets are more fine-grained (i.e. different types of toxicity).
|
| 11 |
+
The model here obatains a test accuracy of 95% on a balanced split.
|