/finch

Deep NLP Examples in TensorFlow 1

Primary LanguageJupyter NotebookMIT LicenseMIT


Contents


Requirements

  • Python 3 and Jupyter Notebook are required

    (CPU User) $ pip3 install tensorflow sklearn scipy bunch tqdm wget
    
    (GPU User) $ pip3 install tensorflow-gpu sklearn scipy bunch tqdm wget
    

Word Embedding(词向量)

Text Classification(文本分类)

Text Generation(文本生成)

  • Language Model(语言模型)

Text Matching(文本匹配)

  • User-Item Matching     Folder

  • Question Matching     Folder

Sequence Labelling(序列标记)

  • POS Tagging(词性识别)

  • Chinese Segmentation(中文分词)

Sequence to Sequence(序列到序列)

  • Learning to Sort(机器排序)

  • Learning to Dialog(机器对话)

  • VAE (Variational Autoencoder)

    • Recurrent VAE     Notebook

      • Variational Inference via tf.distributions     Notebook
    • "Toward Controlled Generation of Text" (ICML 2017)     Folder

  • Data Argumentation(数据增强)

Question Answering(问题回答)

  • Memory Network(记忆网络)

    • End-to-End Memory Network     Notebook

    • Dynamic Memory Network     Notebook

Knowledge Graph(知识图谱)

TensorFlow

  • Loading Data (导入数据)

  • Project Template(项目模版)

    • TF Estimator Template     Folder

    • TF Dataset Template     Folder

Spark

Speech(语音)

Computer Vision(计算机视觉)

Reinforcement Learning(强化学习)