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.

AI Summit: Developing Adventure Game with Free Text Input using NLP

Yusuke Mori  (AI Researcher, SQUARE ENIX CO., LTD)

Location: Room 2002, West Hall

Date: Tuesday, March 21

Time: 1:20 pm - 1:50 pm

Pass Type: All Access Pass, Summits Pass

Topic: Programming

Format: Lecture

Vault Recording: Video

Audience Level: All

In the 1980s, adventure games with free text input, such as Mystery House (On-Line Systems, 1980), was popular. However, due to the technical limitations of the time, the mainstream of adventure games was replaced by those where the user selects explicit commands, which aimed at such free text input by users.

Yusuke Mori, AI Researcher at Square Enix Co, Ltd., will go into how the team has developed a technology for a new generation of adventure games that can flexibly respond to arbitrary input from the user—by utilizing the recent advanced natural language processing (NLP) technology. Using this tech, they have revived one of Japan's most famous adventure games, The Portopia Serial Murder Case (Enix, 1983), in a new form.

Takeaway

Attendees will learn how natural language processing can be applied to adventure games. They implemented two systems using NLP: a text input acceptance system that allows for ambiguity and a chit-chat dialogue system. These allow for a new form of adventure games where users feel a high degree of freedom.

Intended Audience

This is for anyone curious about natural language processing (NLP), especially its application for adventure games. Anyone interested to know how to apply machine learning-based NLP to production and tweak it to the needs of the scenario.