Classifying Multimodal Data Using Transformers

The increasing prevalence of multimodal data in our society has led to the increased need for machines to make sense of such data holistically. However, data scientists and machine learning engineers aspiring to work on such data face challenges fusing the knowledge from existing tutorials which often deal with each mode separately. Drawing on our experience in classifying multimodal municipal issue feedback in the Singapore government, we conduct a hands-on tutorial to help flatten the learning curve for practitioners who want to apply machine learning to multimodal data.