wissamantoun
commited on
Commit
·
68868de
1
Parent(s):
23e2aff
Update README.md
Browse files
README.md
CHANGED
@@ -11,6 +11,8 @@ widget:
|
|
11 |
|
12 |
# AraELECTRA
|
13 |
|
|
|
|
|
14 |
**ELECTRA** is a method for self-supervised language representation learning. It can be used to pre-train transformer networks using relatively little compute. ELECTRA models are trained to distinguish "real" input tokens vs "fake" input tokens generated by another neural network, similar to the discriminator of a [GAN](https://arxiv.org/pdf/1406.2661.pdf). AraELECTRA achieves state-of-the-art results on Arabic QA dataset.
|
15 |
|
16 |
For a detailed description, please refer to the AraELECTRA paper [AraELECTRA: Pre-Training Text Discriminators for Arabic Language Understanding](https://arxiv.org/abs/2012.15516).
|
@@ -39,7 +41,7 @@ It is recommended to apply our preprocessing function before training/testing on
|
|
39 |
```python
|
40 |
from arabert.preprocess import ArabertPreprocessor
|
41 |
|
42 |
-
model_name="araelectra-base"
|
43 |
arabert_prep = ArabertPreprocessor(model_name=model_name)
|
44 |
|
45 |
text = "ولن نبالغ إذا قلنا إن هاتف أو كمبيوتر المكتب في زمننا هذا ضروري"
|
|
|
11 |
|
12 |
# AraELECTRA
|
13 |
|
14 |
+
<img src="https://raw.githubusercontent.com/aub-mind/arabert/master/AraELECTRA.png" width="100" align="left"/>
|
15 |
+
|
16 |
**ELECTRA** is a method for self-supervised language representation learning. It can be used to pre-train transformer networks using relatively little compute. ELECTRA models are trained to distinguish "real" input tokens vs "fake" input tokens generated by another neural network, similar to the discriminator of a [GAN](https://arxiv.org/pdf/1406.2661.pdf). AraELECTRA achieves state-of-the-art results on Arabic QA dataset.
|
17 |
|
18 |
For a detailed description, please refer to the AraELECTRA paper [AraELECTRA: Pre-Training Text Discriminators for Arabic Language Understanding](https://arxiv.org/abs/2012.15516).
|
|
|
41 |
```python
|
42 |
from arabert.preprocess import ArabertPreprocessor
|
43 |
|
44 |
+
model_name="aubmindlab/araelectra-base"
|
45 |
arabert_prep = ArabertPreprocessor(model_name=model_name)
|
46 |
|
47 |
text = "ولن نبالغ إذا قلنا إن هاتف أو كمبيوتر المكتب في زمننا هذا ضروري"
|