Update README.md
Browse files
README.md
CHANGED
|
@@ -28,8 +28,12 @@ Evaluation by class and language:
|
|
| 28 |
|
| 29 |
Based on [BERT multilingual base model (uncased)](https://link.springer.com/article/10.1007/s11192-022-04602-4)
|
| 30 |
|
| 31 |
-
This model is a multilingual version of our [SSciBERT_politics](https://huggingface.co/kalawinka/SSciBERT_politics).
|
| 32 |
-
The
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
|
| 34 |
# Usage
|
| 35 |
|
|
|
|
| 28 |
|
| 29 |
Based on [BERT multilingual base model (uncased)](https://link.springer.com/article/10.1007/s11192-022-04602-4)
|
| 30 |
|
| 31 |
+
This model is a multilingual version of our [SSciBERT_politics](https://huggingface.co/kalawinka/SSciBERT_politics).
|
| 32 |
+
The model was fine-tuned using a dataset of 14,178 abstracts from scientific articles retrieved from the [BASE](https://www.base-search.net/)
|
| 33 |
+
and [POLLUX](https://www.pollux-fid.de/) collections of scientific articles.
|
| 34 |
+
Abstracts from scientific articles in 3 languages (English, German and French) were used for the training.
|
| 35 |
+
The BASE data were labelled as "politics" or "multi" according to the Dewey Decimal Classification (DDC).
|
| 36 |
+
Data from several major political science journals in the POLLUX dataset were marked as "politics" class.
|
| 37 |
|
| 38 |
# Usage
|
| 39 |
|