Update README.md
Browse files
README.md
CHANGED
|
@@ -1,47 +1,34 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
-
|
| 4 |
-
model-index:
|
| 5 |
-
- name: tmpc1bahvp1
|
| 6 |
-
results: []
|
| 7 |
-
---
|
| 8 |
-
|
| 9 |
-
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
| 10 |
-
probably proofread and complete it, then remove this comment. -->
|
| 11 |
-
|
| 12 |
-
# tmpc1bahvp1
|
| 13 |
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
## Model description
|
| 19 |
|
| 20 |
-
|
| 21 |
|
| 22 |
-
|
| 23 |
|
| 24 |
-
|
| 25 |
|
| 26 |
-
## Training
|
| 27 |
|
| 28 |
-
|
| 29 |
|
| 30 |
-
##
|
| 31 |
|
| 32 |
-
|
| 33 |
|
| 34 |
-
|
| 35 |
-
-
|
| 36 |
-
- training_precision: float32
|
| 37 |
|
| 38 |
-
### Training results
|
| 39 |
|
|
|
|
|
|
|
|
|
|
| 40 |
|
|
|
|
| 41 |
|
| 42 |
-
|
| 43 |
|
| 44 |
-
|
| 45 |
-
- TensorFlow 2.9.0
|
| 46 |
-
- Datasets 2.0.0
|
| 47 |
-
- Tokenizers 0.11.6
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- fr
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
|
| 5 |
+
license: mit
|
| 6 |
+
---
|
|
|
|
|
|
|
|
|
|
| 7 |
|
| 8 |
+
# flaubert_small_cased_sentiment
|
| 9 |
|
| 10 |
+
This a `flaubert_small_cased` model finetuned for sentiment analysis on product reviews in French. It predicts the sentiment of the review as a number of stars (between 1 and 5).
|
| 11 |
|
| 12 |
+
This model is intended for direct use as a sentiment analysis model for French product reviews, or for further finetuning on related sentiment analysis tasks.
|
| 13 |
|
| 14 |
+
## Training data
|
| 15 |
|
| 16 |
+
The training data consists of the French portion of `amazon-reviews-multi`, supplemented with another 140,000 similar reviews.
|
| 17 |
|
| 18 |
+
## Accuracy
|
| 19 |
|
| 20 |
+
The finetuned model was evaluated on the French test set of `amazon-reviews-multi`.
|
| 21 |
|
| 22 |
+
- Accuracy (exact) is the exact match on the number of stars.
|
| 23 |
+
- 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.
|
|
|
|
| 24 |
|
|
|
|
| 25 |
|
| 26 |
+
| Language | Accuracy (exact) | Accuracy (off-by-1) |
|
| 27 |
+
| -------- | ---------------------- | ------------------- |
|
| 28 |
+
| French | 61.56% | 95.66%
|
| 29 |
|
| 30 |
+
## Contact
|
| 31 |
|
| 32 |
+
[NLP Town](https://www.nlp.town) offers a suite of sentiment models for a wide range of languages, including an improved multilingual model through [RapidAPI](https://rapidapi.com/nlp-town-nlp-town-default/api/multilingual-sentiment-analysis2/).
|
| 33 |
|
| 34 |
+
Feel free to contact us for questions, feedback and/or requests for similar models.
|
|
|
|
|
|
|
|
|