Cheap and Easy Open-Ended Text Input for Interactive Emergent Narrative

TL;DR

This paper introduces PWIM, a lightweight AI-supported technique that helps players translate high-level text commands into game actions, enhancing open-ended narrative experiences without overwhelming players.

Contribution

It presents a novel, locally runnable sentence embedding-based system for translating player intents into game actions in emergent narrative games.

Findings

Supports open-ended player input effectively

Runs locally on player devices

Reduces player overwhelm in complex game actions

Abstract

We present a demonstration of Play What I Mean (PWIM): a novel, AI-supported interaction technique for interactive emergent narrative (IEN) games and play experiences. By assisting players in translating high-level gameplay intents (expressed as short, unstructured text strings) into concrete game actions, PWIM aims to support open-ended player input while mitigating the overwhelm that players sometimes feel when confronting the large action spaces that characterize IEN gameplay. In matching player intents to game actions, PWIM makes use of an off-the-shelf sentence embedding model that is lightweight enough to run locally on a player's device, and wraps this model in a simple user interface that allows the player to work around occasional classification errors.