참고사이트:

• http://cs224d.stanford.edu/syllabus.html
• http://web.stanford.edu/class/cs224n/syllabus.html
• http://web.stanford.edu/class/cs124/
• http://cs231n.stanford.edu/syllabus.html
• https://web.stanford.edu/~jurafsky/slp3/
• https://github.com/nyu-dl/NLP_DL_Lecture_Note/blob/master/lecture_note.pdf
• https://sites.google.com/view/seq2seq-icml17
• https://khan.github.io/KaTeX/function-support.html
• https://github.com/OpenNMT/OpenNMT-py/
• https://machinelearningmastery.com/applications-of-deep-learning-for-natural-language-processing/ http://ruder.io/deep-learning-nlp-best-practices/
• Oxford NLP lecture notes

앞으로 읽어야 할 것들:

• Text Classificaion
  • Deep Learning for Sentiment Analysis: A Survey
  • Learning to Generate Reviews and Discovering Sentiment
• MT
  • NON-AUTOREGRESSIVE NEURAL MACHINE TRANSLATION
  • WORD TRANSLATION WITHOUT PARALLEL DATA
  • DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding
  • BI-DIRECTIONAL BLOCK SELF-ATTENTION FOR FAST AND MEMORY-EFFICIENT SEQUENCE MODELING
• Summarization
  • Text Summarization Techniques: A Brief Survey
• RL (Policy Gradient)
  • SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
  • BATCH POLICY GRADIENT METHODS FOR IMPROVING NEURAL CONVERSATION MODELS
  • AN ACTOR-CRITIC ALGORITHM FOR SEQUENCE PREDICTION
  • REINFORCEMENT LEARNING NEURAL TURING MACHINES
  • Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback
  • On Monte Carlo Tree Search and Reinforcement Learning
  • DEEP REINFORCEMENT LEARNING: AN OVERVIEW
  • Asynchronous Methods for Deep Reinforcement Learning
  • Evolution Strategies as a Scalable Alternative to Reinforcement Learning
  • A3C Slides
  • Asynchronous Methods for Deep Reinforcement Learning
• Speech Recognition
  • Deep Learning for Speech Recognition @ Cambridge
  • STATE-OF-THE-ART SPEECH RECOGNITION WITH SEQUENCE-TO-SEQUENCE MODELS
  • DeepMind Seminar @ Youtube
  • Stanford Lecture @ Youtube
  • Deep Speech Recognition @ MS
• Chatbot
  • A Deep Reinforcement Learning Chatbot (Short Version)