bsc-temu
commited on
Commit
•
ab7e37c
1
Parent(s):
c1c2dea
Update README.md
Browse files
README.md
CHANGED
@@ -59,11 +59,18 @@ The **roberta-base-ca-cased-sts** is a Semantic Textual Similarity (STS) model f
|
|
59 |
We used the TE dataset in Catalan called [STS-ca](https://huggingface.co/datasets/projecte-aina/sts-ca) for training and evaluation.
|
60 |
|
61 |
## Evaluation and results
|
62 |
-
|
63 |
|
64 |
-
|
|
65 |
-
|
66 |
| BERTa | **81.20** |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
For more details, check the fine-tuning and evaluation scripts in the official [GitHub repository](https://github.com/projecte-aina/berta).
|
68 |
|
69 |
## Citing
|
|
|
59 |
We used the TE dataset in Catalan called [STS-ca](https://huggingface.co/datasets/projecte-aina/sts-ca) for training and evaluation.
|
60 |
|
61 |
## Evaluation and results
|
62 |
+
We evaluated the _roberta-base-ca-cased-sts_ on the STS-ca test set against standard multilingual and monolingual baselines:
|
63 |
|
64 |
+
| Model | STS-ca (Pearson) |
|
65 |
+
|:------------|:----|
|
66 |
| BERTa | **81.20** |
|
67 |
+
| mBERT | 76.34 |
|
68 |
+
| XLM-RoBERTa | 75.40 |
|
69 |
+
| WikiBERT-ca | 77.18 |
|
70 |
+
|
71 |
+
| Task | Model | STS-ca (pearson) |
|
72 |
+
|:------------|:------------|:----|
|
73 |
+
| Semantic Textual Similarity | roberta-base-ca-cased-sts | **81.20** |
|
74 |
For more details, check the fine-tuning and evaluation scripts in the official [GitHub repository](https://github.com/projecte-aina/berta).
|
75 |
|
76 |
## Citing
|