moha commited on
Commit
9f28913
1 Parent(s): 3785882

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -0
README.md CHANGED
@@ -6,6 +6,17 @@ widget:
6
  # arabert_c19: An Arabert model pretrained on 1.5 million COVID-19 multi-dialect Arabic tweets
7
  **mBERT COVID-19** is a pretrained (fine-tuned) version of the mBERT model (https://huggingface.co/bert-base-multilingual-cased). The pretraining was done using 1.5 million multi-dialect Arabic tweets regarding the COVID-19 pandemic from the “Large Arabic Twitter Dataset on COVID-19” (https://arxiv.org/abs/2004.04315).
8
  The model can achieve better results for the tasks that deal with multi-dialect Arabic tweets in relation to the COVID-19 pandemic.
 
 
 
 
 
 
 
 
 
 
 
9
  # Preprocessing
10
  ```python
11
  from arabert.preprocess import ArabertPreprocessor
 
6
  # arabert_c19: An Arabert model pretrained on 1.5 million COVID-19 multi-dialect Arabic tweets
7
  **mBERT COVID-19** is a pretrained (fine-tuned) version of the mBERT model (https://huggingface.co/bert-base-multilingual-cased). The pretraining was done using 1.5 million multi-dialect Arabic tweets regarding the COVID-19 pandemic from the “Large Arabic Twitter Dataset on COVID-19” (https://arxiv.org/abs/2004.04315).
8
  The model can achieve better results for the tasks that deal with multi-dialect Arabic tweets in relation to the COVID-19 pandemic.
9
+
10
+ # Classification results for multiple tasks including fake-news and hate speech detection when using arabert_c19 and mbert_ar_c19:
11
+ For more details refer to the paper (link)
12
+
13
+ | | arabert | mbert | distilbert multi | arabert Covid-19 | mbert Covid-19 |
14
+ |------------------------------------|----------|----------|------------------|------------------|----------------|
15
+ | Contains hate (Binary) | 0.8346 | 0.6675 | 0.7145 | `0.8649` | 0.8492 |
16
+ | Talk about a cure (Binary) | 0.8193 | 0.7406 | 0.7127 | 0.9055 | `0.9176` |
17
+ | News or opinion (Binary) | 0.8987 | 0.8332 | 0.8099 | `0.9163` | 0.9116 |
18
+ | Contains fake information (Binary) | 0.6415 | 0.5428 | 0.4743 | `0.7739` | 0.7228 |
19
+
20
  # Preprocessing
21
  ```python
22
  from arabert.preprocess import ArabertPreprocessor