Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,21 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- summarization
|
4 |
+
- bart
|
5 |
+
|
6 |
+
language:
|
7 |
+
- ar
|
8 |
+
widget:
|
9 |
+
- text: بيروت هي عاصمة <mask>.
|
10 |
+
|
11 |
+
license: apache-2.0
|
12 |
+
|
13 |
+
pipeline_tag: "fill-mask"
|
14 |
+
---
|
15 |
+
|
16 |
+
AraBART is the first Arabic model in which the encoder and the decoder are pretrained end-to-end, based on BART. AraBART follows the architecture of BART-Base
|
17 |
+
which has 6 encoder and 6 decoder layers and 768 hidden dimensions. In total AraBART has 139M parameters.
|
18 |
+
|
19 |
+
AraBART achieves the best performance on multiple abstractive summarization datasets, outperforming strong baselines including a pretrained Arabic BERT-based models and multilingual mBART and mT5 models.
|
20 |
+
|
21 |
+
|