|
--- |
|
language: |
|
- fr |
|
datasets: |
|
- amazon_reviews_multi |
|
license: mit |
|
--- |
|
|
|
# flaubert sentiment |
|
|
|
This is a `flaubert` model finetuned for sentiment analysis on company emails in French. It predicts the sentiment of the email, from `negative` to `positive`. |
|
|
|
This model is intended for direct use as a sentiment analysis model for French emails, or for further finetuning on related sentiment analysis tasks. |
|
|
|
## Training data |
|
|
|
The training data consists of the French portion of `emails_multi`, supplemented with another 40,000 similar emails. |
|
|
|
## Accuracy |
|
|
|
The finetuned model was evaluated on the French test set of `emails_multi`. |
|
|
|
- Accuracy (exact) is the exact match on the number of stars. |
|
- Accuracy (off-by-1) is the percentage of reviews where the number of stars the model predicts differs by a maximum of 1 from the number given by the human reviewer. |
|
|
|
|
|
| Language | Accuracy (exact) | |
|
| -------- | ---------------------- |
|
| French |95% | |
|
|
|
|
