language: sl
tags:
- text-classification
- hate-speech
widget:
- text: Silva, ti si grda in neprijazna.
Text classification model based on EMBEDDIA/sloberta and fine-tuned on the FRANK dataset comprising of LGBT and migrant hatespeech. Only the slovenian subset of the data was used for fine-tuning and the dataset has been relabeled for binary classification (offensive or acceptable).
Fine-tuning hyperparameters
Fine-tuning was performed with simpletransformers. Beforehand a brief hyperparameter optimisation was performed and the presumed optimal hyperparameters are:
model_args = {
"num_train_epochs": 14,
"learning_rate": 1e-5,
"train_batch_size": 21,
}
Performance
The same pipeline was run with two other transformer models and fasttext for comparison. Accuracy and macro F1 score were recorded for each of the 6 fine-tuning sessions and post festum analyzed.
| model | average accuracy | average macro F1 |
|---|---|---|
| sloberta-frenk-hate | 0.7785 | 0.7764 |
| EMBEDDIA/crosloengual-bert | 0.7616 | 0.7585 |
| xlm-roberta-base | 0.686 | 0.6827 |
| fasttext | 0.721 | 0.711 |
From recorded accuracies and macro F1 scores p-values were also calculated:
Comparison with crosloengual-bert:
| test | accuracy p-value | macro F1 p-value |
|---|---|---|
| Wilcoxon | 0.00781 | 0.00781 |
| Mann Whithney U test | 0.00163 | 0.00108 |
| Student t-test | 0.000101 | 3.95e-05 |
Comparison with xlm-roberta-base:
| test | accuracy p-value | macro F1 p-value |
|---|---|---|
| Wilcoxon | 0.00781 | 0.00781 |
| Mann Whithney U test | 0.00108 | 0.00108 |
| Student t-test | 9.46e-11 | 6.94e-11 |
Use examples
from simpletransformers.classification import ClassificationModel
model_args = {
"num_train_epochs": 6,
"learning_rate": 3e-6,
"train_batch_size": 69}
model = ClassificationModel(
"camembert", "5roop/sloberta-frenk-hate", use_cuda=True,
args=model_args
)
predictions, logit_output = model.predict(["Silva, ti si grda in neprijazna", "Naša hiša ima dimnik"])
predictions
### Output:
### array([1, 0])