Tutorial in Chinese can be found in mofanpy.com.

This repo includes many simple implementations of models in Neural Language Processing (NLP).

All code implementations in this tutorial are organized as following:

1. Search Engine

• TF-IDF numpy / TF-IDF skearn

2. Understand Word (W2V)

• Continuous Bag of Words (CBOW)
• Skip-Gram

3. Understand Sentence (Seq2Seq)

• seq2seq
• CNN language model

4. All about Attention

• seq2seq with attention
• Transformer

5. Pretrained Models

• ELMo
• GPT
• BERT

Thanks for the contribution made by @W1Fl with a simplified keras codes in simple_realize

$ git clone https://github.com/MorvanZhou/NLP-Tutorials
$ cd NLP-Tutorials/
$ sudo pip3 install -r requirements.txt

TF-IDF numpy code

TF-IDF short sklearn code

Efficient Estimation of Word Representations in Vector Space

Skip-Gram code

CBOW code

Sequence to Sequence Learning with Neural Networks

Seq2Seq code

Convolutional Neural Networks for Sentence Classification

CNN language model code

Effective Approaches to Attention-based Neural Machine Translation

Seq2Seq Attention code

Attention Is All You Need

Transformer code

Deep contextualized word representations

ELMO code

Improving Language Understanding by Generative Pre-Training

GPT code

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

BERT code

My new attempt Bert with window mask