This graduate-level course offers a comprehensive exploration of Natural Language Processing (NLP), focusing on how machines process, understand, and generate human language. It covers both Natural Language Understanding (NLU), which involves interpreting and extracting meaning from text (e.g., named entity recognition, sentiment analysis, and machine reading comprehension), and Natural Language Generation (NLG), which focuses on producing coherent and contextually relevant text (e.g., text summarization, machine translation, and paraphrase generation). Students will delve into the different linguistic levels required for NLP, including morphology, lexical analysis, syntax, semantics, pragmatics, and discourse analysis, to understand language structures comprehensively. The course also introduces cutting-edge technologies, such as transformer-based models like BERT, GPT, and T5, which have revolutionized NLP with their ability to handle complex tasks through pre-training and fine-tuning. Additionally, students will explore both traditional machine learning models (e.g., Naive Bayes, SVMs) and advanced deep learning architectures (e.g., RNNs, LSTMs, and transformers), understanding their applications in tasks like sequence modeling and language generation. By the end of the course, participants will have hands-on experience with modern NLP tools and techniques, gaining the skills needed to develop state-of-the-art NLP solutions for real-world applications.