This course provides a structured introduction to Natural Language Processing (NLP), combining theoretical principles with practical insights. It begins with a general overview of NLP and its applications, followed by coverage of several key components, including word embeddings, vector space models, and the prominent deep learning architectures that have significantly advanced the field, such as RNNs, LSTMs, and Transformers. It also explores Large Language Models (LLMs) like GPT and BERT, as well as evaluation methods to assess the effectiveness and limitations of NLP technologies. Overall, the course is designed to offer an overview of and insight into the mainstream techniques of NLP, ensuring that students gain a solid understanding of both foundational concepts and advanced technologies. This prepares them for further academic or professional engagement in the field.