Update README.md
Browse files
README.md
CHANGED
|
@@ -7,12 +7,16 @@ license: apache-2.0
|
|
| 7 |
|
| 8 |
Submitted to LREC 2026
|
| 9 |
|
| 10 |
-
|
| 11 |
|
| 12 |
BERnaT is a family of monolingual Basque encoder-only language models trained to better represent linguistic variation—including standard, dialectal, historical, and informal Basque—rather than focusing solely on standard textual corpora. Models were trained on corpora that combine high-quality standard Basque with varied sources such as social media and historical texts, aiming to enhance robustness and generalization across natural language understanding (NLU) tasks.
|
| 13 |
|
| 14 |
-
**
|
| 15 |
-
**
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Training Data
|
| 18 |
|
|
|
|
| 7 |
|
| 8 |
Submitted to LREC 2026
|
| 9 |
|
| 10 |
+
### Model Description
|
| 11 |
|
| 12 |
BERnaT is a family of monolingual Basque encoder-only language models trained to better represent linguistic variation—including standard, dialectal, historical, and informal Basque—rather than focusing solely on standard textual corpora. Models were trained on corpora that combine high-quality standard Basque with varied sources such as social media and historical texts, aiming to enhance robustness and generalization across natural language understanding (NLU) tasks.
|
| 13 |
|
| 14 |
+
- **Developed by:** HiTZ Research Center & IXA Research group (University of the Basque Country UPV/EHU)
|
| 15 |
+
- **Funded by:** Ikergaitu and ALIA projects (Basque and Spanish Government)
|
| 16 |
+
- **License:** Apache 2.0
|
| 17 |
+
- **Model Type**: Encoder-only Transformer models (RoBERTa-style)
|
| 18 |
+
- **Languages**: Basque (Euskara)
|
| 19 |
+
|
| 20 |
|
| 21 |
## Training Data
|
| 22 |
|