About Norms and Causes

TL;DR

This paper introduces a method to extract domain norms from texts by analyzing descriptions of deviations from these norms, demonstrated through driving-related texts.

Contribution

It presents a novel approach to identify implicit norms in texts by leveraging cause-and-effect language, specifically applied to the driving domain.

Findings

Successfully identified basic driving norms from textual descriptions.

Validated the approach with algorithms that detect implicit norms in driving texts.

Showed that cause descriptions often reveal underlying norms.

Abstract

Knowing the norms of a domain is crucial, but there exist no repository of norms. We propose a method to extract them from texts: texts generally do not describe a norm, but rather how a state-of-affairs differs from it. Answers concerning the cause of the state-of-affairs described often reveal the implicit norm. We apply this idea to the domain of driving, and validate it by designing algorithms that identify, in a text, the "basic" norms to which it refers implicitly.