CS 395T: Topics in Natural Language Processing
In this course, we discuss three topics in NLP (generation, question answering, grounding), and machine learning methods introduced to address these topics. Each topic discussion will span multiple classes: we will first study how the research problems have been framed, and discuss the advances and limitations of machine learning methods designed to address the problem. The class will include, in addition to paper reviews and discussions, a final group project. This course focuses on identifying research problems in NLP and understanding existing methods to address such research problems. The course does not require a prior background in NLP, but a background in programming and machine learning.
Course Time and LocationLecture: 9:30AM-11:00AM, Tuesdays and Thursdays
This course is designed for graduate students and highly motivated undergraduates who are interested in the up to date research in natural language processing. The NLP courses offered at UT-Austin (graduate level or undergraduate level) is not a prerequisite for this course, but will provide solid grounds for this course. Throughout the course, you will learn
- cutting-edge research in natural processing, focusing on three major topics (generation, question answering, and grounding). You will learn recent progresses and remaining challenges in each area, and prepare to perform research yourself.
- how to formulate and evaluate NLP problems and develop solutions for them.
- how to read and criticize research papers and communicate research both orally and in writing.
Students are expected to have the following backgrounds:
- Coursework related to 391L - Machine Learning (or equivalent)
- Coursework related to 311 or 311H - Discrete Math for Computer Science (or equivalent)
- Familiarity with Python (for the final project)
- Additional prior exposure to probability, linear algebra, optimization, linguistics, and NLP recommended but not required
Note: This course is an advanced graduate-level course. If you are unclear whether you meet these requirements, please consult the instructor in advance (email your CV and transcript).
Note: If you would like to take the course but wasn't able to register or would like to audit, please reach out to the instructor..
Credits: Yuke Zhu for the website format.