I'm trying to do a project where I have paragraphs and I need to classify them into multiple labels. The dataset is around 40k rows with labels. I understand there is no one right approach but should I consider typical ML classifiers like embeddings + Logistic regression, xgboost etc. Or should I directly consider fine tuning transformers like BERT,DistilBERT etc.

My priority is on getting accurate predictions and I have a few weeks to complete this.



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.