I have a question- answer data set with multi-label target in one column , i want to classify each question to multi-label how i should start working with it ? do i need to put each label in one column? and how i'll do that ?
If you have one column storing the labelset of each instance, it might be easier to use the Label Powerset (LP) approach to create your first model.
Chapter Mining Multi-label Data
If you have familiar with deep learning you can use transfer-learning dan multi-label classification. You can see the short explanation as follow: https://androidkt.com/multi-label-text-classification-in-tensorflow-keras/
Article Instance Based Classification for Decision Making in Network Data
I suggest you to follow : https://www.depends-on-the-definition.com/guide-to-multi-label-classification-with-neural-networks/
https://www.pyimagesearch.com/2018/05/07/multi-label-classification-with-keras/
- Badges
- Science topic
- Similar topics
- Analytical Chemistry
- Column