The paper presents the Japanese Tort-case Dataset (JTD), a novel tool for predicting legal judgments in Japanese tort cases. The dataset features two tasks: tort prediction and rationale extraction. The rationale extraction task identifies the court’s accepted arguments from the alleged arguments by plaintiffs and defendants. The JTD was constructed from 3,477 annotated judgments by 41 legal experts, and includes 7,978 instances with 59,697 alleged arguments. The paper also discusses the role of machine learning techniques in LJP and the need for large datasets for training and evaluating ML models.
Publication date: 4 Dec 2023
Project Page: Not provided
Paper: https://arxiv.org/pdf/2312.00480
