Playing by the Book: An Interactive Game Approach for Action Graph Extraction from Text

TL;DR

This paper introduces Text2Quest, an innovative interactive game-based method for extracting action graphs from specialized procedural texts, particularly in material science, by simulating instructions in a text-based environment to improve understanding.

Contribution

The paper presents a novel interactive game approach for action graph extraction, leveraging simulation to enhance learning from complex, specialized procedural texts.

Findings

Prototype proof-of-concept released

Enables richer learning compared to static methods

Potential to improve information extraction in scientific texts

Abstract

Understanding procedural text requires tracking entities, actions and effects as the narrative unfolds. We focus on the challenging real-world problem of action-graph extraction from material science papers, where language is highly specialized and data annotation is expensive and scarce. We propose a novel approach, Text2Quest, where procedural text is interpreted as instructions for an interactive game. A learning agent completes the game by executing the procedure correctly in a text-based simulated lab environment. The framework can complement existing approaches and enables richer forms of learning compared to static texts. We discuss potential limitations and advantages of the approach, and release a prototype proof-of-concept, hoping to encourage research in this direction.