Natural Language Processing

This course provides a comprehensive introduction to Natural Language Processing (NLP), tracing its evolution from rule-based systems to modern machine learning approaches. Students will learn foundational techniques such as text preprocessing, tokenization, stemming, lemmatization, and word embeddings, enabling machines to interpret the semantic meaning of words in context. The course explores deep learning architectures like Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks, essential for tasks like language modeling and machine translation.

Advanced topics include transformer architectures, such as Generative Pretrained Transformers (GPT) and Bidirectional Encoder Representations from Transformers (BERT). Students will gain hands-on experience in applying these cutting-edge models to NLP tasks and designing end-to-end NLP pipelines. By the end of the course, participants will be equipped to tackle complex NLP challenges using state-of-the-art tools and techniques.

Course Highlights:

•    Hands-On Learning:  Create Python scripts for text processing and build NLP models using Google Colaboratory or Jupyter Notebooks
•    Foundational Knowledge:  Explore text preprocessing, word embeddings, and basic machine learning classification techniques
•    Deep Learning Techniques:  Implement RNNs, LSTMs, transformers, and GPT/BERT models for advanced language tasks
•    Real-World Applications:  Develop and deploy end-to-end NLP pipelines.
•    Career Preparation:  Gain proficiency in the latest NLP tools and techniques for professional roles in AI and data science


Course Learning Outcomes:

Upon successful completion of this course, students will be able to:

•    Develop Python programs for NLP tasks using machine learning libraries
•    Implement text preprocessing techniques like tokenization and normalization
•    Analyze and use word embeddings (e.g., TF-IDF, Word2Vec, GloVe) for document similarity and classification
•    Design and train neural networks, including encoder-decoder and transformer models
•    Build and deploy end-to-end NLP solutions using modern frameworks and methodologies


Course Typically Offered: Online in Winter and Summer quarters

Software: Students will use Python to complete hands-on assignments. These tools are free and open-source

Hardware: Students must have access to a web-enabled computer

Prerequisites: CSE-40028 Introduction to Programming (Python) or equivalent practical experience, and linear algebra, probability and statistics skills

Next Step: After completing of this course, consider taking other courses in the Machine Learning Methods, Technical Aspects of Artificial Intelligence or Python Programming certificate


Contact: For more information about this cousre, please contact us at unex-techdata@ucsd.edu