Natural Language Processing is one of the most important branches of artificial intelligence. Its goal is to create an interaction channel between humans and machines through natural human language. This course introduces fundamental NLP concepts and basic methods for solving related problems, while also covering some state-of-the-art approaches.

1. Course Introduction and Objectives (1 session)
   • Overview of course content and syllabus
2. Introduction to Natural Language Processing (1 session)
   • NLP overview, brief history, key problems and challenges
3. Text Preprocessing Methods (2 sessions)
   • Regular expressions, tokenization, normalization, stemming/lemmatization, sentence boundary detection, MED distance calculation
4. Language Models (2 sessions)
   • Basic language modeling, n-grams, perplexity, smoothing techniques
5. Basic Text Classification Methods (3 sessions)
   • Classification concepts, feature extraction, simple classifiers, logistic regression for classification, extending logistic regression to neural networks
6. Basic Text Clustering Methods (2 sessions)
   • Clustering concepts, k-means and mixture models
7. Word Representations (4 sessions)
   • Word representation methods: basic approaches, linear algebra-based methods, neural network-based methods, challenges and solutions, context-based representations (basic introduction)
8. Machine Translation (4 sessions)
   • Traditional machine translation models, IBM models, phrase-based models
9. Recurrent Neural Networks and Attention Models (3 sessions)
   • Simple RNNs and popular architectures (LSTM, GRU), modern machine translation models, attention mechanisms
10. Parsing in NLP (3 sessions)
    • Semantic and syntactic parsing types
    • Basic parsing models
11. Other NLP Applications (3 sessions)
    • Additional NLP tasks: information extraction, summarization, POS tagging, etc.

• Practical Assignments and Final Seminar: 30%
• Midterm Exam: 20%
• Final Exam: 30%
• Final Project: 20%