https://github.com/mhagiwara/100-nlp-papers

RNN

LSTM

GRU

How LSTM - Vanishing gradients

Attention

Evaluation Metrics

Distance Metrics and Visualizations

Beam Search

Misc

Gradient clipping:

Paper Reading

Misc.

CBOW and SkipGram

Optimized CBOW and SkipGram (Word2Vec)

GloVe

FastText

RNN LM & BPTT