Automated Action Model Acquisition from Narrative Texts

TL;DR

NaRuto is an unsupervised system that automatically extracts high-quality action models from narrative texts, improving planning in AI by addressing the bottleneck of manual model creation.

Contribution

The paper introduces NaRuto, a novel unsupervised approach for extracting action models from narrative texts, outperforming existing automated methods.

Findings

NaRuto generates action models of significantly better quality than existing automated methods.

NaRuto's models are comparable to semi-automated approaches in quality.

Experimental results demonstrate NaRuto's effectiveness in classical narrative planning domains.

Abstract

Action models, which take the form of precondition/effect axioms, facilitate causal and motivational connections between actions for AI agents. Action model acquisition has been identified as a bottleneck in the application of planning technology, especially within narrative planning. Acquiring action models from narrative texts in an automated way is essential, but challenging because of the inherent complexities of such texts. We present NaRuto, a system that extracts structured events from narrative text and subsequently generates planning-language-style action models based on predictions of commonsense event relations, as well as textual contradictions and similarities, in an unsupervised manner. Experimental results in classical narrative planning domains show that NaRuto can generate action models of significantly better quality than existing fully automated methods, and even on par with those of semi-automated methods.