Multi-label text classification with Naive Bayes and DistilBERT

We predict the genres of a movie from its summary (overview).

• First: Applying a classical Naive Bayes, cleaning (normalization, stop-words and stemming) and transforming the text with TF-IDF.
• Second: Applying DistilBERT on raw and tokenized text.

How to run it?

• Open the notebook in kaggle https://www.kaggle.com/jaimemorillo/genre-prediction-with-distilbert.
• Click on "Copy & Edit".
• Enable GPU accelerator (optional) and Internet.
• Enjoy running it.

Note: You must be registered and phone verified to use GPU and have Internet connection.