GDC is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

View, browse and sort the ever-growing list of sessions by day, pass type, topic, and format. With this Session Viewer, you can view GDC 2023 session details and speakers, and share your favorites via social media. You will be able to build your schedule and access it during the show via export or Mobile App, once live. Sessions do fill up and seating is first come, first serve, so arrive early to sessions that you would like to attend.

Machine Learning Summit: Natural Language Generation for Games Writing

Ben Swanson  (Research Scientist, Ubisoft)

Location: Room 2010, West Hall

Date: Tuesday, March 21

Time: 10:50 am - 11:50 am

Pass Type: All Access Pass, Summits Pass

Topic: Programming

Format: Lecture

Vault Recording: Video

Audience Level: All

It is the ambition of many games to create a simulation of a world containing NPCs, and in most cases these NPCs need to have something to say. They may be talking to the player, to each other, or to themselves—but they must speak without hesitation, repetition, or deviation from the narrative design.

In this session, Ben Swanson, Research Scientist at Ubisoft, will present a system that allows the narrative designer to seed their designs with first draft text that can then be accepted, edited, or regenerated by writers at the click of a button, unlocking the ability to scale up narrative systems to accompany larger and more complex worlds.


Attendees will gain an understanding of the potential for large language models as data augmentation engines, the power of using pairwise comparison as a method for evaluation of natural language generation tools, and an appreciation of not just how money can be saved but how new experiences are enabled by AI assistive tools.

Intended Audience

This is for narrative designers, technical narrative designers, and writers—but also, more broadly, those interested in how large language models can impact the content creation pipeline.