Update README.md
Browse files
README.md
CHANGED
|
@@ -20,23 +20,29 @@ model-index:
|
|
| 20 |
results: []
|
| 21 |
---
|
| 22 |
|
| 23 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 24 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 25 |
-
|
| 26 |
# uzroberta-sentiment-analysis
|
| 27 |
|
| 28 |
-
This
|
| 29 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
It achieves the following results on the evaluation set:
|
| 31 |
- Loss: 0.5718
|
| 32 |
- Precision: 0.9113
|
| 33 |
- Recall: 0.8869
|
| 34 |
-
- F1: 0.8989
|
| 35 |
- Accuracy: 0.896
|
| 36 |
|
| 37 |
## Model description
|
| 38 |
|
| 39 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
|
| 41 |
## Intended uses & limitations
|
| 42 |
|
|
|
|
| 20 |
results: []
|
| 21 |
---
|
| 22 |
|
|
|
|
|
|
|
|
|
|
| 23 |
# uzroberta-sentiment-analysis
|
| 24 |
|
| 25 |
+
This is a roBERTa-base model trained on ~23K reviews(~323K words) and finetuned for sentiment analysis of customer reviews. This model is built as part of author's project at the Uz-NLP 2022 Hackathon and it is suitable for Uzbek language.
|
| 26 |
+
|
| 27 |
+
<b>Labels</b>:
|
| 28 |
+
0 -> Negative;
|
| 29 |
+
1 -> Positive
|
| 30 |
+
|
| 31 |
It achieves the following results on the evaluation set:
|
| 32 |
- Loss: 0.5718
|
| 33 |
- Precision: 0.9113
|
| 34 |
- Recall: 0.8869
|
| 35 |
+
- F1 Score: 0.8989
|
| 36 |
- Accuracy: 0.896
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
| 40 |
+
This model is a fine-tuned version of [rifkat/uztext-3Gb-BPE-Roberta](https://huggingface.co/rifkat/uztext-3Gb-BPE-Roberta) on the [Uzbek App reviews for Sentiment Classification](https://github.com/SanatbekMatlatipov/uzbek-sentiment-analysis) dataset. It achieves the following results on the evaluation set:
|
| 41 |
+
- Loss: 0.5718
|
| 42 |
+
- Precision: 0.9113
|
| 43 |
+
- Recall: 0.8869
|
| 44 |
+
- F1 Score: 0.8989
|
| 45 |
+
- Accuracy: 0.896
|
| 46 |
|
| 47 |
## Intended uses & limitations
|
| 48 |
|