C S 574
Download as PDF
Transformer Models for Natural Language Processing
Computer Science
College of Physical and Mathematical Sciences
Course Description
Understand and learn how to use state of the art transformer language models for many Natural Language Processing and Understanding tasks, such as text classification, text generation, question answering, machine translation, and many other tasks.
When Taught
Fall
Fixed
3
Fixed
3
Fixed
0
Title
Transformer Model
Learning Outcome
Students will study and demonstrate understanding of the transformer model and multi-headed attention mechanisms.
Title
Transformers for NLP
Learning Outcome
Students will demonstrate understanding and develop code that uses transformer models for many Natural Language Processing tasks such as text classification, named entity recognition, question answering, and summarization.
Title
Generative Models
Learning Outcome
Students will develop generative transformer models to generate appropriate text for a project of their choice.
Title
Zero Shot and Few Shot Learning
Learning Outcome
Students will demonstrate understanding of zero shot and few shot learning and prompt engineering for generative models.
Title
Scaling
Learning Outcome
Students will demonstrate understanding of scaling methods for large language models such as distillation, quantization, as well as methods for training models with small amounts of training data.
