NLP-Tutorial

---

---

• NLP-Tutorial
  • 项目实例
    • 1.基础模型(Logistic,Word2Vec)
    • 2.卷积神经网络(CNN)
    • 3.循环神经网络(RNN,LSTM,Bi-LSTM)
    • 4.序列模型(Seq2Seq,Attention)
    • 5.Model based on Transformer(Transformer,BERT)
  • Dependencies
  • Author
  • Reference

---

项目实例

1.基础模型(Logistic,Word2Vec)

• 1.Logistic - 文本情感二分类

  • Paper - A maximum entropy approach to natural language processing(1996)
  • Colab - Logistic.ipynb
• 2. Word2Vec(Skip-gram) - 生成文本嵌入矩阵并可视化
  • Paper - Distributed Representations of Words and Phrases and their Compositionality(2013)
  • Colab - Word2Vec.ipynb

2.卷积神经网络(CNN)

• 3. TextCNN - 文本情感二分类
  • Paper - Convolutional Neural Networks for Sentence Classification(2014)
  • Colab - TextCNN.ipynb

3.循环神经网络(RNN,LSTM,Bi-LSTM)

• 4. TextRNN - 预测下一个单词
  • Paper - Finding Structure in Time(1990)
  • Colab - TextRNN.ipynb
• 5. TextLSTM - 预测单词下一个字母
  • Paper - LONG SHORT-TERM MEMORY(1997)
  • Colab - TextLSTM.ipynb
• 6. Bi-LSTM - 在长句中预测下一个单词
  • Paper - Bidirectional Long Short-Term Memory Networks for Relation Classification(2015)
  • Colab - Bi_LSTM.ipynb

4.序列模型(Seq2Seq,Attention)

• 7. Seq2Seq - 单词翻译
  • Paper - Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation(2014)
  • Colab - Seq2Seq.ipynb
• 8. Seq2Seq with Attention - 句子翻译
  • Paper - Neural Machine Translation by Jointly Learning to Align and Translate(2014)
  • Colab - Seq2Seq(Attention).ipynb
• 9. Bi-LSTM with Attention - 文本情感二分类
  • Paper - Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification(2016)
  • Colab - Bi_LSTM(Attention).ipynb

5.Model based on Transformer(Transformer,BERT)

• 10. The Transformer - 机器翻译
  • Paper - Attention Is All You Need(2017)
  • Colab - Transformer.ipynb
• 11. BERT - 预测掩码标记和句间关系判断
  • Paper - BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding(2018)
  • Colab - BERT.ipynb

---

Dependencies

• Python 3.6+
• Pytorch 1.0.0+
• numpy 1.10.0+

---

Author

• Cheng Junkai @github.com/Cheng0829
• Email : [email protected]
• Site : CSDN & 博客园

---

Reference

• 本项目基于NLP-Tutorial进行了改写,并添加了大量中文注释和markdown笔记内容