Affordance Extraction with an External Knowledge Database for Text-Based Simulated Environments

TL;DR

This paper explores using external knowledge bases like ConceptNet to automatically extract affordances in text-based simulated environments, aiding in generating interaction commands for AI agents.

Contribution

It introduces an automated affordance extraction algorithm utilizing external knowledge databases and evaluates its effectiveness on TextWorld and Jericho platforms.

Findings

External databases can be used for affordance extraction despite challenges

Automated affordance extraction can generate viable interaction commands

Human baseline study validates the quality of the automated process

Abstract

Text-based simulated environments have proven to be a valid testbed for machine learning approaches. The process of affordance extraction can be used to generate possible actions for interaction within such an environment. In this paper the capabilities and challenges for utilizing external knowledge databases (in particular ConceptNet) in the process of affordance extraction are studied. An algorithm for automated affordance extraction is introduced and evaluated on the Interactive Fiction (IF) platforms TextWorld and Jericho. For this purpose, the collected affordances are translated into text commands for IF agents. To probe the quality of the automated evaluation process, an additional human baseline study is conducted. The paper illustrates that, despite some challenges, external databases can in principle be used for affordance extraction. The paper concludes with recommendations for further modification and improvement of the process.