Update README.md
Browse files
README.md
CHANGED
@@ -1,25 +1,13 @@
|
|
1 |
---
|
2 |
license: cc-by-sa-4.0
|
|
|
|
|
3 |
---
|
4 |
|
5 |
### xlm-roberta-base for register labeling, specifically fine-tuned for question-answer document identification
|
6 |
|
7 |
This is the `xlm-roberta-base`, fine-tuned on register annotated data in English (https://github.com/TurkuNLP/CORE-corpus) and Finnish (https://github.com/TurkuNLP/FinCORE_full) as well as unpublished versions of Swedish and French (https://github.com/TurkuNLP/multilingual-register-labeling). The model is trained to predict whether a text includes something related to questions and answers or not.
|
8 |
|
9 |
-
### Overview
|
10 |
-
Language model: xlm-roberta-base
|
11 |
-
|
12 |
-
Downstream-task: multi-class text classification
|
13 |
-
|
14 |
-
|
15 |
-
### Usage
|
16 |
-
|
17 |
-
the model can be used through a huggingface pipeline:
|
18 |
-
```
|
19 |
-
model = transformers.AutoModelForSequenceClassification.from_pretrained("TurkuNLP/xlmr-qa-register")
|
20 |
-
tokenizer = transformers.AutoTokenizer.from_pretrained("xlm-roberta-base")
|
21 |
-
pipe = transformers.pipeline(task="text-classification", model=model, tokenizer=tokenizer)
|
22 |
-
```
|
23 |
|
24 |
### Hyperparameters
|
25 |
```
|
|
|
1 |
---
|
2 |
license: cc-by-sa-4.0
|
3 |
+
library_name: transformers
|
4 |
+
pipeline_tag: text-classification
|
5 |
---
|
6 |
|
7 |
### xlm-roberta-base for register labeling, specifically fine-tuned for question-answer document identification
|
8 |
|
9 |
This is the `xlm-roberta-base`, fine-tuned on register annotated data in English (https://github.com/TurkuNLP/CORE-corpus) and Finnish (https://github.com/TurkuNLP/FinCORE_full) as well as unpublished versions of Swedish and French (https://github.com/TurkuNLP/multilingual-register-labeling). The model is trained to predict whether a text includes something related to questions and answers or not.
|
10 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
|
12 |
### Hyperparameters
|
13 |
```
|