Awesome
Awesome Transformer
A curated list of NLP resources focused on Transformer.
What is Transformer?
Transformer is a novel neural network architecture which has shown great promise in many natural language processing(NLP) tasks such as machine translation, language modeling, question answering and reading comprehension.
<img src="https://github.com/basicv8vc/awesome-transformer/blob/master/imgs/transformer.png" width = "500" height = "700" alt="The Transformer - model architecture " align=center />More info here.
Table of Contents
Implementations
repository | framework | organization |
---|---|---|
tensor2tensor | TensorFlow(official) | |
allennlp | PyTorch | Allen AI |
annotated-transformer | PyTorch | Harvard NLP |
attention-is-all-you-need-pytorch | PyTorch | jadore801120 |
gluon-nlp | MXNet | dmlc |
attention-is-all-you-need-keras | Keras | Lsdefine |
attention_is_all_you_need | Chainer | soskek |
Theory
Lectures
lecture | course | school |
---|---|---|
Transformers and Self-Attention For Generative Models | CS224n: Natural Language Processing with Deep Learning | Stanford |
Self Attention/CNNs | CS 11-731 Machine Translation and Sequence-to-Sequence Models | CMU |
Attention | CS 11-747 Neural Networks for NLP | CMU |
Attention | CSC 421/2516 Neural Networks and Deep Learning | Toronto |