Fastai with 🤗Transformers (BERT, RoBERTa, XLNet, XLM, DistilBERT)
A tutorial to implement state-of-the-art NLP models with Fastai for Sentiment Analysis.
NB. This article was originally published here on Towards Data Science.
In early 2018, Jeremy Howard (co-founder of fast.ai) and Sebastian Ruder introduced the Universal Language Model Fine-tuning for Text Classification (ULMFiT) method. ULMFiT was the first Transfer Learning method applied to NLP. As a result, besides significantly outperforming many state-of-the-art tasks, it allowed, with only 100 labeled examples, to match performances equivalent to models trained on 100× more data.