Commit
•
c2b379e
1
Parent(s):
3ba308b
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
Model BERTuit as presented in the [BERTuit: Understanding Spanish language in Twitter through a native transformer](https://arxiv.org/abs/2204.03465) article.
|
| 2 |
|
| 3 |
-
Before tokenization replace user tags and urls with "
|
| 4 |
|
| 5 |
Tokenize text with base class RoBERTaTokenizer.
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: masked-language-modeling
|
| 3 |
+
tags:
|
| 4 |
+
- online social networks
|
| 5 |
+
- twitter
|
| 6 |
+
- spanish
|
| 7 |
+
language: es
|
| 8 |
+
license: apache-2.0
|
| 9 |
+
widget:
|
| 10 |
+
- text: "Las <mask> causan hipoxia."
|
| 11 |
+
example_title: "Natural Language Inference"
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
Model BERTuit as presented in the [BERTuit: Understanding Spanish language in Twitter through a native transformer](https://arxiv.org/abs/2204.03465) article.
|
| 15 |
|
| 16 |
+
Before tokenization replace user tags and urls with "\<usr\>" and "\<url\>" respectively.
|
| 17 |
|
| 18 |
Tokenize text with base class RoBERTaTokenizer.
|