The University of Texas at Austin
Fall 2025
Instructor: Jessy Li
This course is co-designed by:
Modern artificial intelligence systems are able to translate, summarize, make small talk, and even generate a poem or a story. But how do they achieve these abilities? And what does it take for machines to understand how sentences connect together and produce longer stretches of text? In this course we discuss (1) discourse structure, i.e., computational models of document structure, relationship between sentences, and coherence; and (2) natural langauge generation (NLG) systems including machine translation, summarization, and story generation. This course introduces machine learning/neural network models for discourse processing and text generation. We will also touch upon open issues in NLG, including evaluation, ethics, and factuality.
| Grade | Percentage |
|---|---|
| A | >= 93% |
| A- | >= 90% |
| B+ | >= 87% |
| B | >= 83% |
| B- | >= 80% |
| C+ | >= 77% |
| C | >= 73% |
| C- | >= 70% |
| D+ | >= 67% |
| D | >= 63% |
| D- | >= 60% |
You are encouraged to discuss assignments with classmates. But all coding/written work must be your own. You are not allowed to collaborate with other students directly on code and submit shared code as part of two more more students’ submissions, unless this is explicitly allowed as in the case of the final project.
Note that you may consult external resources such as blog posts, YouTube videos, academic papers, GitHub repositories, and more. However, your use of such resources, particularly GitHub repositories, must be limited in the same way as discussions with other students: you can look at these to get an idea of how to solve a problem, but you should not take external code and submit it as part of your assignment.
Be sure you respect these policies when posting on the discussion board. Asking clarifying questions, addressing possible bugs in the provided code, etc. are fair game, but you should discuss solutions in a substantive way that might spoil them for others. When in doubt, do not post large amounts of source code publicly to the class.
Students who violate these policies may receive a failing grade on the assignment in question or for the course overall, depending on the instructors’ judgment and the severity of the infraction.
We encourage you to use ChatGPT and other related tools to understand concepts and as an assistant with the programming assignments in this class. Understanding the capabilities of these systems and their boundaries is a major focus of this class, and there’s no better way to do that than by using them! You are allowed to use these tools for programming assignments. However, usage of ChatGPT must be limited in the same way as usage of other resources discussed above. You should come up with the high-level skeleton of the solution yourself and use these tools primarily as coding assistants.
An example of a good question is, “Write a line of Python code to set probabilities below [min_p] to 0” during decoding. Similar invocation of Copilot will probably be useful as well.
An example of a bad question would be to try to feed in a large chunk of the assignment code and copypaste the problem specification from the assignment PDF. This is also much less likely to be useful, as it might be hard to spot subtle bugs.
As a heuristic, it should be possible for you to explain what each line of your code is doing. If you have code in your solution that is only included because ChatGPT told you to put it there, then it is no longer your own work in the same way.
If in doubt, ask the instructor.
The University of Texas at Austin provides upon request appropriate academic accommodations for qualified students with disabilities. Please contact the Division of Diversity and Community Engagement, Services for Students with Disabilities, 512-471-6259.
A student who cannot meet an assignment deadline due to the observance of a religious holy day may submit the assignment up to 24 hours late without penalty, if proper notice of the planned absence has been given. Notice must be given at least 14 days prior to the due date. For religious holy days that fall within the first 2 weeks of the semester, notice should be given on the first day of the semester. Notice should be emailed to the instructor and course staff.
Schedule is tentative and subject to change.