Update README.md
Browse files
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 |
-
|
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)
|