m-nagoudi commited on
Commit
dab4afb
1 Parent(s): d345174

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -4
README.md CHANGED
@@ -1,16 +1,22 @@
 
 
 
 
 
 
 
1
  <img src="https://github.com/UBC-NLP/turjuman/raw/master/images/turjuman.png" alt="AraT5" width="50%" height="50%" align="right"/>
2
 
3
 
4
 
5
-
6
- <img src="./images/turjuman.png" alt="AraT5" width="55%" height="55%" align="right"/>
7
-
8
  Turjuman is a neural machine translation toolkit. It translates from 20 languages into Modern Standard Arabic (MSA). Turjuman is described in this paper:
9
  [**TURJUMAN: A Public Toolkit for Neural Arabic Machine Translation**](https://arxiv.org/abs/2206.03933).
10
 
11
  Turjuman exploits our [AraT5 model](https://github.com/UBC-NLP/araT5). This endows Turjuman with a powerful ability to decode into Arabic. The toolkit offers the possibility of employing a number of diverse decoding methods, making it suited for acquiring paraphrases for the MSA translations as an added value.
12
 
13
- <br>
14
  **Github**: [https://github.com/UBC-NLP/turjuman](https://github.com/UBC-NLP/turjuman)
 
15
  **Demo**: [https://demos.dlnlp.ai/turjuman](https://demos.dlnlp.ai/turjuman)
 
16
  **Paper**: [https://arxiv.org/abs/2206.03933](https://arxiv.org/abs/2206.03933)
 
1
+
2
+ <p align="center">
3
+ <br>
4
+ <img src="https://github.com/UBC-NLP/turjuman/raw/master//images/turjuman_logo.png"/>
5
+ <br>
6
+ <p>
7
+
8
  <img src="https://github.com/UBC-NLP/turjuman/raw/master/images/turjuman.png" alt="AraT5" width="50%" height="50%" align="right"/>
9
 
10
 
11
 
 
 
 
12
  Turjuman is a neural machine translation toolkit. It translates from 20 languages into Modern Standard Arabic (MSA). Turjuman is described in this paper:
13
  [**TURJUMAN: A Public Toolkit for Neural Arabic Machine Translation**](https://arxiv.org/abs/2206.03933).
14
 
15
  Turjuman exploits our [AraT5 model](https://github.com/UBC-NLP/araT5). This endows Turjuman with a powerful ability to decode into Arabic. The toolkit offers the possibility of employing a number of diverse decoding methods, making it suited for acquiring paraphrases for the MSA translations as an added value.
16
 
17
+
18
  **Github**: [https://github.com/UBC-NLP/turjuman](https://github.com/UBC-NLP/turjuman)
19
+
20
  **Demo**: [https://demos.dlnlp.ai/turjuman](https://demos.dlnlp.ai/turjuman)
21
+
22
  **Paper**: [https://arxiv.org/abs/2206.03933](https://arxiv.org/abs/2206.03933)