Classifying Norm Conflicts using Learned Semantic Representations
This work addresses the problem of improving productivity and reliability in contract analysis for contract makers, though it appears incremental as it builds on previous approaches.
The paper tackles the problem of automatically detecting and classifying normative conflicts in contracts, which are time-consuming and error-prone to identify manually, by introducing an approach that converts contracts into latent representations and trains a model to classify conflicts into four types, achieving new state-of-the-art results.
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.