Deconstructing BERT: Distilling 6 Patterns from 100 Million Parameters | by Jesse Vig | Towards Data Science

The year 2018 marked a turning point for the field of Natural Language Processing, with a series of deep-learning models achieving state-of-the-art results on NLP tasks ranging from question… — Lees op towardsdatascience.com/deconstructing-bert-distilling-6-patterns-from-100-million-parameters-b49113672f77