# Classifying Norm Conflicts using Learned Semantic Representations

## TL;DR

This paper presents an automated method to detect and classify normative conflicts in contracts by transforming norms into semantic representations, improving accuracy over previous approaches.

## Contribution

The authors introduce a novel approach that converts contract norms into latent semantic representations and classifies conflicts into four types, achieving state-of-the-art results.

## Key findings

- Achieved new state-of-the-art accuracy in conflict classification
- Successfully modeled both syntactic and semantic features of norms
- Demonstrated effectiveness on real contract data

## Abstract

While most social norms are informal, they are often formalized by companies in contracts to regulate trades of goods and services. When poorly written, contracts may contain normative conflicts resulting from opposing deontic meanings or contradict specifications. As contracts tend to be long and contain many norms, manually identifying such conflicts requires human-effort, which is time-consuming and error-prone. Automating such task benefits contract makers increasing productivity and making conflict identification more reliable. To address this problem, we introduce an approach to detect and classify norm conflicts in contracts by converting them into latent representations that preserve both syntactic and semantic information and training a model to classify norm conflicts in four conflict types. Our results reach the new state of the art when compared to a previous approach.