Update README.md
Browse files
README.md
CHANGED
@@ -21,8 +21,6 @@ $$P(premise=c\in\{contradiction, entailment, neutral\}\vert hypothesis)$$
|
|
21 |
### Language-agnostic approach
|
22 |
It should be noted that hypotheses and premises are randomly chosen between English and French, with each language combination representing a probability of 25%.
|
23 |
|
24 |
-
### Detaset
|
25 |
-
|
26 |
### Performance
|
27 |
|
28 |
| **class** | **precision (%)** | **f1-score (%)** | **support** |
|
@@ -56,6 +54,9 @@ is the sentence we aim to classify.
|
|
56 |
|
57 |
### Performance
|
58 |
|
|
|
|
|
|
|
59 |
| **model** | **accuracy (%)** | **MCC (x100)** |
|
60 |
| :--------------: | :--------------: | :------------: |
|
61 |
| [cmarkea/distilcamembert-base-nli](https://huggingface.co/cmarkea/distilcamembert-base-nli) | 80.59 | 63.71 |
|
|
|
21 |
### Language-agnostic approach
|
22 |
It should be noted that hypotheses and premises are randomly chosen between English and French, with each language combination representing a probability of 25%.
|
23 |
|
|
|
|
|
24 |
### Performance
|
25 |
|
26 |
| **class** | **precision (%)** | **f1-score (%)** | **support** |
|
|
|
54 |
|
55 |
### Performance
|
56 |
|
57 |
+
The model is evaluated based on sentiment analysis evaluation on the French film review site [Allociné](https://huggingface.co/datasets/allocine). The dataset is labeled
|
58 |
+
into 2 classes, positive comments and negative comments. We then use the hypothesis template "Ce commentaire est {}. and the candidate classes "positif" and "negatif".
|
59 |
+
|
60 |
| **model** | **accuracy (%)** | **MCC (x100)** |
|
61 |
| :--------------: | :--------------: | :------------: |
|
62 |
| [cmarkea/distilcamembert-base-nli](https://huggingface.co/cmarkea/distilcamembert-base-nli) | 80.59 | 63.71 |
|