bsc-temu
commited on
Commit
•
9e93af0
1
Parent(s):
aa8f365
Update README.md
Browse files
README.md
CHANGED
@@ -38,10 +38,15 @@ The **roberta-base-ca-cased-qa** is a Question Answering (QA) model for the Cata
|
|
38 |
We used the QA dataset in Catalan called [ViquiQuAD](https://huggingface.co/datasets/projecte-aina/viquiquad) for training and evaluation, and the [XQuAD-ca](https://huggingface.co/datasets/projecte-aina/xquad-ca) test set for evaluation.
|
39 |
|
40 |
## Evaluation and results
|
|
|
41 |
|
42 |
-
|
43 |
-
|
|
44 |
-
|
|
|
|
|
|
|
|
|
|
45 |
|
46 |
For more details, check the fine-tuning and evaluation scripts in the official [GitHub repository](https://github.com/projecte-aina/berta).
|
47 |
|
38 |
We used the QA dataset in Catalan called [ViquiQuAD](https://huggingface.co/datasets/projecte-aina/viquiquad) for training and evaluation, and the [XQuAD-ca](https://huggingface.co/datasets/projecte-aina/xquad-ca) test set for evaluation.
|
39 |
|
40 |
## Evaluation and results
|
41 |
+
We evaluated the _roberta-base-ca-cased-qa_ on the ViquiQuAD and XQuAD-ca test sets against standard multilingual and monolingual baselines:
|
42 |
|
43 |
+
|
44 |
+
| Model | ViquiQuAD (F1/EM) | XQuAD-ca (F1/EM) |
|
45 |
+
| ------------|:-------------:| -----:|
|
46 |
+
| roberta-base-ca-cased-qa | **86.99/73.25** | **67.81/49.43** |
|
47 |
+
| mBERT | 86.97/72.22 | 67.15/46.51 |
|
48 |
+
| XLM-RoBERTa | 85.50/70.47 | 67.10/46.42 |
|
49 |
+
| WikiBERT-ca | 85.45/70.75 | 65.21/36.60 |
|
50 |
|
51 |
For more details, check the fine-tuning and evaluation scripts in the official [GitHub repository](https://github.com/projecte-aina/berta).
|
52 |
|