Update README.md
Browse files
README.md
CHANGED
|
@@ -73,7 +73,7 @@ model-index:
|
|
| 73 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 74 |
should probably proofread and complete it, then remove this comment. -->
|
| 75 |
|
| 76 |
-
#
|
| 77 |
|
| 78 |
This model is a fine-tuned version of [readerbench/RoBERT-base](https://huggingface.co/readerbench/RoBERT-base) on the None dataset.
|
| 79 |
It achieves the following results on the evaluation set:
|
|
@@ -84,6 +84,10 @@ It achieves the following results on the evaluation set:
|
|
| 84 |
- F1: 0.8652
|
| 85 |
- F1 Weighted: 0.8287
|
| 86 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 87 |
### Evaluation on other datasets
|
| 88 |
|
| 89 |
**SENT_RO**
|
|
@@ -125,6 +129,8 @@ Sentiment classification for Romanian Language.
|
|
| 125 |
|
| 126 |
Biased towards Product reviews.
|
| 127 |
|
|
|
|
|
|
|
| 128 |
## Training and evaluation data
|
| 129 |
|
| 130 |
**Trained on:**
|
|
|
|
| 73 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 74 |
should probably proofread and complete it, then remove this comment. -->
|
| 75 |
|
| 76 |
+
# RO-Sentiment
|
| 77 |
|
| 78 |
This model is a fine-tuned version of [readerbench/RoBERT-base](https://huggingface.co/readerbench/RoBERT-base) on the None dataset.
|
| 79 |
It achieves the following results on the evaluation set:
|
|
|
|
| 84 |
- F1: 0.8652
|
| 85 |
- F1 Weighted: 0.8287
|
| 86 |
|
| 87 |
+
Output labels:
|
| 88 |
+
- LABEL_0 = Negative Sentiment
|
| 89 |
+
- LABEL_1 = Positive Sentiment
|
| 90 |
+
|
| 91 |
### Evaluation on other datasets
|
| 92 |
|
| 93 |
**SENT_RO**
|
|
|
|
| 129 |
|
| 130 |
Biased towards Product reviews.
|
| 131 |
|
| 132 |
+
There is no "neutral" sentiment label.
|
| 133 |
+
|
| 134 |
## Training and evaluation data
|
| 135 |
|
| 136 |
**Trained on:**
|