Catalog Description: This course provides a hands-on introduction to language technologies, covering methods for processing speech and text. This includes: statistical models, early neural models, and transformer-based LLMs; model architectures, training, evaluation, and social impacts; core tasks and methods like machine translation, parsing, and prompting; analysis and representation of speech and speech recognition models. Weekly assignments provide practical experience in building systems and understanding their strengths and limitations.

Units: 4

Prerequisites: COMPSCI C182, COMPSCI 188, or COMPSCI 189

Credit Restrictions: Students will receive no credit for EECS 283A after completing COMPSCI 288. A deficient grade in EECS 283A may be removed by taking COMPSCI 288.

Formats:
Spring: 3.0 hours of lecture and 1.0 hours of discussion per week
Fall: 3.0 hours of lecture and 1.0 hours of discussion per week

Grading Basis: letter

Final Exam Status: Written final exam conducted during the scheduled final exam period

---

Links:

• CS enrollment policies
• EE enrollment policies
• HKN course maps