Foundation of Language Models and Processing

Catalog description

This course provides a comprehensive introduction to the foundational concepts, models, and recent advancements in Natural Language Processing (NLP). Students will explore traditional NLP techniques such as part-of-speech tagging and syntactic parsing, as well as modern deep learning models, including recurrent neural networks (RNNs), Transformer architectures, and large language models (LLMs). The course emphasizes the practical use of NLP in real-world applications such as question answering, text summarization, sentiment analysis, and machine translation. Through programming assignments and hands-on projects, students will gain experience using Python and widely adopted NLP libraries such as spaCy, HuggingFace, and NLTK. By the end of the course, students will be able to apply state-of-the-art NLP models to address real-world language processing problems.