CS224N: Goals of the Course

• Objective: Understand the fundamentals of Natural Language Processing (NLP) and its intersection with Deep Learning.
• Key Topics:
  1. Introduction to NLP and Deep Learning.
  2. Word vectors and embeddings.
  3. Basics of Neural Networks.
  4. Dependency parsing.
  5. Recurrent Neural Networks (RNNs) and LSTMs.
  6. Machine Translation and Sequence-to-Sequence models.
  7. Attention mechanisms.
  8. Convolutional Neural Networks (CNNs) for NLP.
  9. Sentiment analysis and opinion mining.
  10. Transfer learning for NLP.
  11. Coreference resolution.
  12. Constituency and Dependency Parsing.
  13. Question answering.
  14. Dialogue and Conversational Agents.
• Overall Focus: Equip students with the knowledge and skills to apply deep learning techniques to solve a range of NLP problems.
• Practical Applications: Learn to build models for tasks such as sentiment analysis, machine translation, and question answering.
• Critical Thinking: Develop a critical understanding of challenges in NLP and how deep learning approaches address them.
• Research Exploration: Encourage exploration of cutting-edge research in NLP through assignments and projects.
• Hands-On Experience: Gain practical experience in implementing and training NLP models using popular deep learning frameworks.
• Collaboration and Communication: Foster collaborative skills by working on projects and communicating findings effectively.
• Preparation for Advanced Studies: Lay the foundation for further exploration in advanced NLP and deep learning research.

Lecture 1: Intro and Word Vectors

Lecture 2: Word Vectors, Word Senses, and Neural Classifiers