Deep-Learning-for-NLP

Contains different course tutorials and jupyter notebook file for applying different Deep Learning models in different NLP tasks such as text classification, summarization, translation, etc.

Contents

1. Introduction

• basic concepts
• Text representation, BoW, Word vectors

2. Text classification and Sentiment Analysis

• Naive Bayes
• Logistic Regression
• fastText model
• Deep models
  • RNNs and LSTMs
  • Convolutional neural networks for text classification
  • RCNN (Recurrent convolutional neural networks for text classification
  • AWD LSTMs and ULFiT approach
  • Transformers (Bert, XLNet, etc.)

3. Neural Machine Translation

4. Text summarization

5. Other NLP tasks

Getting started

Reference