https://github.com/graykode/nlp-tutorial

Jupyter Notebook
Natural Language Processing Tutorial for Deep Learning Researchers

nlp-tutorial

nlp-tutorial is a tutorial for who is studying NLP(Natural Language Processing) using TensorFlow and Pytorch. Most of the models in NLP were implemented with less than 100 lines of code.(except comments or blank lines)

Curriculum - (Example Purpose)

1. Basic Embedding Model

• 1-1. NNLM(Neural Network Language Model) - Predict Next Word
  • Paper - A Neural Probabilistic Language Model(2003)
  • Colab - NNLM_Tensor.ipynb, NNLM_Torch.ipynb
• 1-2. Word2Vec(Skip-gram) - Embedding Words and Show Graph
  • Paper - Distributed Representations of Words and Phrases and their Compositionality(2013)
  • Colab - Word2Vec_Tensor(NCE_loss).ipynb, Word2Vec_Tensor(Softmax).ipynb, Word2Vec_Torch(Softmax).ipynb
• 1-3. FastText(Application Level) - Sentence Classification
  • Paper - Bag of Tricks for Efficient Text Classification(2016)
  • Colab - FastText.ipynb

2. CNN(Convolutional Neural Network)

• 2-1. TextCNN - Binary Sentiment Classification
  • Paper - Convolutional Neural Networks for Sentence Classification(2014)
  • Colab - TextCNN_Tensor.ipynb, TextCNN_Torch.ipynb
• 2-2. DCNN(Dynamic Convolutional Neural Network)

3. RNN(Recurrent Neural Network)

• 3-1. TextRNN - Predict Next Step
  • Paper - Finding Structure in Time(1990)
  • Colab - TextRNN_Tensor.ipynb, TextRNN_Torch.ipynb
• 3-2. TextLSTM - Autocomplete
  • Paper - LONG SHORT-TERM MEMORY(1997)
  • Colab - TextLSTM_Tensor.ipynb, TextLSTM_Torch.ipynb
• 3-3. Bi-LSTM - Predict Next Word in Long Sentence
  • Colab - Bi_LSTM_Tensor.ipynb, Bi_LSTM_Torch.ipynb

4. Attention Mechanism

• 4-1. Seq2Seq - Change Word
  • Paper - Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation(2014)
  • Colab - Seq2Seq_Tensor.ipynb, Seq2Seq_Torch.ipynb
• 4-2. Seq2Seq with Attention - Translate
  • Paper - Neural Machine Translation by Jointly Learning to Align and Translate(2014)
  • Colab - Seq2Seq(Attention)_Tensor.ipynb, Seq2Seq(Attention)_Torch.ipynb
• 4-3. Bi-LSTM with Attention - Binary Sentiment Classification
  • Colab - Bi_LSTM(Attention)_Tensor.ipynb, Bi_LSTM(Attention)_Torch.ipynb

5. Model based on Transformer

• 5-1. The Transformer - Translate
  • Paper - Attention Is All You Need(2017)
  • Colab - Transformer_Torch.ipynb, Transformer(Greedy_decoder)_Torch.ipynb
• 5-2. BERT - Classification Next Sentence & Predict Masked Tokens
  • Paper - BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding(2018)
  • Colab - BERT_Torch.ipynb

Model	Example	Framework	Lines(torch/tensor)
NNLM	Predict Next Word	Torch, Tensor	67/83
Word2Vec(Softmax)	Embedding Words and Show Graph	Torch, Tensor	77/94
TextCNN	Sentence Classification	Torch, Tensor	94/99
TextRNN	Predict Next Step	Torch, Tensor	70/88
TextLSTM	Autocomplete	Torch, Tensor	73/78
Bi-LSTM	Predict Next Word in Long Sentence	Torch, Tensor	73/78
Seq2Seq	Change Word	Torch, Tensor	93/111
Seq2Seq with Attention	Translate	Torch, Tensor	108/118
Bi-LSTM with Attention	Binary Sentiment Classification	Torch, Tensor	92/104
Transformer	Translate	Torch	222/0
Greedy Decoder Transformer	Translate	Torch	246/0
BERT	how to train	Torch	242/0

Dependencies

• Python 3.5+
• Tensorflow 1.12.0+
• Pytorch 0.4.1+
• Plan to add Keras Version

Author

• Tae Hwan Jung(Jeff Jung) @graykode
• Author Email : nlkey2022@gmail.com
• Acknowledgements to mojitok as NLP Research Internship.