tarrade / proj_multilingual_text_classification

Explore multilingal text classification using embedding, bert and deep learning architecture
Apache License 2.0
4 stars 1 forks source link

Ideal Architecture for Fine-Tuning #53

Closed vluechinger closed 4 years ago

vluechinger commented 4 years ago

When adding a larger network on top of BERT instead of just a simple classificationhead, does that improve the results?

What is the effect of adding additional layers or e.g. a CNN?