Information Extraction/Entailment of Common Law and Civil Code

With the recent advancements in machine learning models, we have seen improvements in Natural Language Inference (NLI) tasks, but legal entailment has been challenging, particularly for supervised approaches. In this paper, we evaluate different approaches on handling entailment tasks for small domain-specific data sets provided in the Competition on Legal Information Extraction/Entailment (COLIEE). This year COLIEE had four tasks, which focused on legal information processing and finding textual entailment on legal data. We participated in all the four tasks this year, and evaluated different kinds of approaches, including classification, ranking, and transfer learning approaches against the entailment tasks. In some of the tasks, we achieved competitive results when compared to simpler rule-based approaches, which so far have dominated the competition for the last six years.