Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Which course? Discourse! Teaching Discourse and Generation in the Era of LLMs

Junyi Jessy Li, Yang Janet Liu, Kanishka Misra, Valentina Pyatkin, William Sheffield

TL;DR

The paper addresses the need for cross-disciplinary NLP education that bridges discourse processing and natural language generation in the era of large language models. It presents a new upper-level undergraduate course at UT Austin that threads discourse theory (coherence, entity tracking, QUD) into NLG practice, combining lectures, mini-workshops, and open-ended projects. The study details course design, content, assignments, and a formative evaluation, reporting strong student engagement and perceived impact, along with challenges such as compute resources and scalability. The work demonstrates a practical path to cultivate researchers and practitioners who can critically assess and advance long-form, discourse-aware NLP systems, with implications for future curriculum design and research directions.

Abstract

The field of NLP has undergone vast, continuous transformations over the past few years, sparking debates going beyond discipline boundaries. This begs important questions in education: how do we design courses that bridge sub-disciplines in this shifting landscape? This paper explores this question from the angle of discourse processing, an area with rich linguistic insights and computational models for the intentional, attentional, and coherence structure of language. Discourse is highly relevant for open-ended or long-form text generation, yet this connection is under-explored in existing undergraduate curricula. We present a new course, "Computational Discourse and Natural Language Generation". The course is collaboratively designed by a team with complementary expertise and was offered for the first time in Fall 2025 as an upper-level undergraduate course, cross-listed between Linguistics and Computer Science. Our philosophy is to deeply integrate the theoretical and empirical aspects, and create an exploratory mindset inside the classroom and in the assignments. This paper describes the course in detail and concludes with takeaways from an independent survey as well as our vision for future directions.

Which course? Discourse! Teaching Discourse and Generation in the Era of LLMs

TL;DR

The paper addresses the need for cross-disciplinary NLP education that bridges discourse processing and natural language generation in the era of large language models. It presents a new upper-level undergraduate course at UT Austin that threads discourse theory (coherence, entity tracking, QUD) into NLG practice, combining lectures, mini-workshops, and open-ended projects. The study details course design, content, assignments, and a formative evaluation, reporting strong student engagement and perceived impact, along with challenges such as compute resources and scalability. The work demonstrates a practical path to cultivate researchers and practitioners who can critically assess and advance long-form, discourse-aware NLP systems, with implications for future curriculum design and research directions.

Abstract

The field of NLP has undergone vast, continuous transformations over the past few years, sparking debates going beyond discipline boundaries. This begs important questions in education: how do we design courses that bridge sub-disciplines in this shifting landscape? This paper explores this question from the angle of discourse processing, an area with rich linguistic insights and computational models for the intentional, attentional, and coherence structure of language. Discourse is highly relevant for open-ended or long-form text generation, yet this connection is under-explored in existing undergraduate curricula. We present a new course, "Computational Discourse and Natural Language Generation". The course is collaboratively designed by a team with complementary expertise and was offered for the first time in Fall 2025 as an upper-level undergraduate course, cross-listed between Linguistics and Computer Science. Our philosophy is to deeply integrate the theoretical and empirical aspects, and create an exploratory mindset inside the classroom and in the assignments. This paper describes the course in detail and concludes with takeaways from an independent survey as well as our vision for future directions.
Paper Structure (29 sections, 2 figures)

This paper contains 29 sections, 2 figures.

Table of Contents

  1. Introduction
  2. Motivation and Inspirations
  3. Design Principles
  4. Threading Discourse within NLG.
  5. Mini Workshops for Concept Grounding.
  6. Exposure to Research.
  7. Exploration, Not Just Problem Solving.
  8. Accessibility for Diverse Backgrounds.
  9. Collaborative Design of Content.
  10. Course Content
  11. Content on LLMs and Generation
  12. Language Modeling and NLG.
  13. RL Overview and Applications.
  14. Demos.
  15. Content on Discourse
  16. ...and 14 more sections

Figures (2)

  • Figure 1: Perceived learning outcomes by topic.
  • Figure 2: Academic/career impact.