Contracts formally represent agreements between two or more parties as deontic statements or norms within their clauses. Norms may conflict between each other if not carefully designed, which may invalidate entire contracts. Human reviewers invest great effort to write conflict-free contracts that, for complex and long contracts, can be time-consuming and error-prone. In this work, we develop an approach to automate the identification of potential conflicts between norms in contracts. We build a two-phase approach that uses traditional machine learning together with a convolutional neural network to extract and compare norms in order to identify conflicts between them. Using a manually annotated and artificially generated set of conflicts as train and test set, our approach obtains 84% accuracy.
|Title of host publication||Coordination, Organizations, Institutions, Norms, and Ethics for Governance of Multi-Agent Systems XIII|
|Subtitle of host publication||COIN COINE 2017 2020|
|Editors||A Aler Tubella, S Cranefield, C Frantz, F Meneguzzi, W Vasconcelos|
|Publication status||Published - 2 Apr 2021|
|Name||Lecture Notes in Computer Science|
- Deep learning
- Natural language