hate-alert / de-limit Goto Github PK

Hello,

Can you provide a sample of the code that can be used to carry out a prediction using your model, on a new sentence or tweet for example?

Thank you!

I am currently trying to reproduce the results reported in Table 3. of the research paper. So far, I have tried to use "bert-base-multilingual-cased/uncased" as the pre-trained model for the French dataset(9a). However, the results on the test dataset do not match with those reported in the paper. I am not sure if I am using the correct pre-trained model and python packages. A few package versions in requirements.txt seem outdated and cause the training/inference script to break.

Could you please provide some guidance on how I should go about this?

Thanks in advance.

in the CNN_GRU.py file at the training phase, the Eval_phase_cnngru function was used but there is no definition anywhere.

remove details from api_config,py

I got the following error when I use your dehatebert-mono-arabic with Chris McCormick code :
RuntimeError: Error(s) in loading state_dict for BertForSequenceClassification:
size mismatch for classifier.weight: copying a param with shape torch.Size([2, 768]) from checkpoint, the shape in current model is torch.Size([3, 768]).
size mismatch for classifier.bias: copying a param with shape torch.Size([2]) from checkpoint, the shape in current model is torch.Size([3]).

Looking through your Translation.ipynb code, your READ.ME in Dataset folder costs nothing. No description for how to name and store datasets provided. You mention full_data folder, but files must be stored in train, test and val folders.

It comes from
train_files = glob.glob('train/*.csv')
test_files = glob.glob('test/*.csv')
val_files = glob.glob('val/*.csv')
files= train_files+test_files+val_files

Fix it please!

When running project, there is an error "No matching distribution found for api_config"
How can i fix this?