Norm Based Causal Reasoning in Textual Corpus

TL;DR

This paper introduces a norm-based causal reasoning system that enhances natural language understanding by inferring implicit information, addressing limitations of truth-based entailments, and applying it to accident analysis from textual descriptions.

Contribution

It formalizes a norm-based reasoning approach for causal inference in natural language, improving understanding of implicit information in texts.

Findings

Successfully infers causes of accidents from textual descriptions

Demonstrates the effectiveness of norm-based reasoning in NLP

Addresses limitations of traditional truth-based entailments

Abstract

Truth based entailments are not sufficient for a good comprehension of NL. In fact, it can not deduce implicit information necessary to understand a text. On the other hand, norm based entailments are able to reach this goal. This idea was behind the development of Frames (Minsky 75) and Scripts (Schank 77, Schank 79) in the 70's. But these theories are not formalized enough and their adaptation to new situations is far from being obvious. In this paper, we present a reasoning system which uses norms in a causal reasoning process in order to find the cause of an accident from a text describing it.