Natural Language Processing

Catalog description

This course offers a comprehensive exploration of both foundational and advanced techniques in NLP, including modern deep learning methodologies. Designed for students who have completed an introduction to deep learning, the course covers a range of topics from syntactic parsing and language modeling to state-of-the-art transformer architectures and large language models (LLMs) like BERT and GPT. Students will gain hands-on experience through labs and projects, which involve using popular NLP tools and libraries to build applications such as sentiment analysis systems, translation systems, and retrieval-augmented generation (RAG) systems. Emphasizing practical skills and ethical considerations, this course prepares students for research and industry roles in AI, computational linguistics, and data science. Course Learning Outcomes 1. Have solid understanding of key NLP concepts and techniques, both traditional and deep learning-based. 2. Develop proficiency in essential NLP tasks, such as tokenization, syntactic parsing, part-of-speech tagging, and statistical language modeling. 3. Gain hands-on experience with neural network architectures, including RNNs, LSTMs, and transformers, and learn to leverage pre-trained models like BERT and GPT for various NLP applications. 4. Master the use of APIs for large language models, enabling them to build real-world applications, such as conversational agents and text summarization tools. 5. Critically assess the ethical and societal implications of deploying NLP technologies, particularly in the context of large language models, ensuring they are prepared for responsible and impactful work in the field. View Class Schedule