Add multilingual to the language tag
#1
by
lbourdois
- opened
README.md
CHANGED
@@ -2,14 +2,14 @@
|
|
2 |
language:
|
3 |
- tr
|
4 |
- de
|
|
|
|
|
|
|
|
|
5 |
datasets:
|
6 |
- mc4
|
7 |
- wikipedia
|
8 |
- multilexnorm
|
9 |
-
tags:
|
10 |
-
- lexical normalization
|
11 |
-
license: apache-2.0
|
12 |
-
|
13 |
---
|
14 |
|
15 |
# Fine-tuned ByT5-small for MultiLexNorm (Turkish-German version)
|
@@ -23,14 +23,14 @@ Our system is based on [ByT5](https://arxiv.org/abs/2105.13626), which we first
|
|
23 |
|
24 |
## How to use
|
25 |
|
26 |
-
The model was *not* fine-tuned in a standard sentence-to-sentence setting
|
27 |
|
28 |
|
29 |
## How to cite
|
30 |
|
31 |
```bibtex
|
32 |
@inproceedings{wnut-ufal,
|
33 |
-
title= "{
|
34 |
author = "Samuel, David and Straka, Milan",
|
35 |
booktitle = "Proceedings of the 7th Workshop on Noisy User-generated Text (W-NUT 2021)",
|
36 |
year = "2021",
|
|
|
2 |
language:
|
3 |
- tr
|
4 |
- de
|
5 |
+
- multilingual
|
6 |
+
license: apache-2.0
|
7 |
+
tags:
|
8 |
+
- lexical normalization
|
9 |
datasets:
|
10 |
- mc4
|
11 |
- wikipedia
|
12 |
- multilexnorm
|
|
|
|
|
|
|
|
|
13 |
---
|
14 |
|
15 |
# Fine-tuned ByT5-small for MultiLexNorm (Turkish-German version)
|
|
|
23 |
|
24 |
## How to use
|
25 |
|
26 |
+
The model was *not* fine-tuned in a standard sentence-to-sentence setting � instead, it was tailored to the token-to-token definition of MultiLexNorm data. Please refer to [**the interactive demo on Colab notebook**](https://colab.research.google.com/drive/1rxpI8IlKk-D2crFqi2hdzbTBIezqgsCg?usp=sharing) to learn how to use these models.
|
27 |
|
28 |
|
29 |
## How to cite
|
30 |
|
31 |
```bibtex
|
32 |
@inproceedings{wnut-ufal,
|
33 |
+
title= "{�FAL} at {MultiLexNorm} 2021: Improving Multilingual Lexical Normalization by Fine-tuning {ByT5}",
|
34 |
author = "Samuel, David and Straka, Milan",
|
35 |
booktitle = "Proceedings of the 7th Workshop on Noisy User-generated Text (W-NUT 2021)",
|
36 |
year = "2021",
|