Regenerate model card
Browse files
README.md
CHANGED
|
@@ -27,12 +27,9 @@ The Dutch model uses ``FacebookAI/xlm-roberta-base`` as its base encoder and is
|
|
| 27 |
|
| 28 |
## Evaluation
|
| 29 |
|
| 30 |
-
| Metric |
|
| 31 |
-
| ------ | -- |
|
| 32 |
-
|
|
| 33 |
-
| Words | 99.80 |
|
| 34 |
-
| Sentences | 97.10 |
|
| 35 |
-
|
| 36 |
|
| 37 |
|
| 38 |
## Usage
|
|
@@ -83,7 +80,7 @@ The training data license: cc-by-nc-sa-4.0 is derived from the Universal Depende
|
|
| 83 |
|
| 84 |
If you use this model, please cite:
|
| 85 |
|
| 86 |
-
Ulewicz, M., & Wr贸blewska, A. (2026). *COMBO-SEG Models Trained on UD v2.17*.
|
| 87 |
|
| 88 |
```bibtex
|
| 89 |
@software{combo_seg_2026,
|
|
@@ -96,8 +93,6 @@ Ulewicz, M., & Wr贸blewska, A. (2026). *COMBO-SEG Models Trained on UD v2.17*. Z
|
|
| 96 |
}
|
| 97 |
```
|
| 98 |
|
| 99 |
-
|
| 100 |
-
|
| 101 |
## Resources
|
| 102 |
|
| 103 |
- COMBO-SEG: [https://gitlab.clarin-pl.eu/syntactic-tools/combo-seg](https://gitlab.clarin-pl.eu/syntactic-tools/combo-seg)
|
|
|
|
| 27 |
|
| 28 |
## Evaluation
|
| 29 |
|
| 30 |
+
| Metric | Tokens | Words | Sentences |
|
| 31 |
+
| ------ | ------ | ----- | --------- |
|
| 32 |
+
| F1 | 99.83 | 99.80 | 97.10 |
|
|
|
|
|
|
|
|
|
|
| 33 |
|
| 34 |
|
| 35 |
## Usage
|
|
|
|
| 80 |
|
| 81 |
If you use this model, please cite:
|
| 82 |
|
| 83 |
+
Ulewicz, M., & Wr贸blewska, A. (2026). *COMBO-SEG Models Trained on UD v2.17*. https://doi.org/10.5281/zenodo.19651441
|
| 84 |
|
| 85 |
```bibtex
|
| 86 |
@software{combo_seg_2026,
|
|
|
|
| 93 |
}
|
| 94 |
```
|
| 95 |
|
|
|
|
|
|
|
| 96 |
## Resources
|
| 97 |
|
| 98 |
- COMBO-SEG: [https://gitlab.clarin-pl.eu/syntactic-tools/combo-seg](https://gitlab.clarin-pl.eu/syntactic-tools/combo-seg)
|