Hello all
Actually, I want to perform text classification using Bert algorithm on a text dataset that is imbalanced . I want to balance my data but first convert text to vector and then balance my data. but I don't know how do this work as Bert has a special tokenizer.
thank you for your help
Hello Abhinav Kathuria
I asked about this subject in my page last week. then I got good results with using stratified sampling. as follows:
X_train, X_val, y_train, y_val = train_test_split(df.index.values, df.label.values, test_size=0.15, random_state=42, stratify=df.label.values)
I hope this helps you.
Hello Mahsa Mirzaei
I have assigned weights to different classes, that is the only way i think to balance the classes before applying BERT. But i want to ask, if we can apply cross validation to BERT model. Please explain
- Badges
- Science topic
- Similar topics
- Physical Sciences
- Atomic, Molecular and Optical Physics
- Atoms