...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Expert systems: The international journal of knowledge engineering >Prediction of court decision from Arabic documents using deep learning
【24h】

Prediction of court decision from Arabic documents using deep learning

机译：Prediction of court decision from Arabic documents using deep learning

获取原文
获取原文并翻译 | 示例
   

获取外文期刊封面封底 >>

       
页面导航
  • 摘要
  • 著录项
  • 相关主题

摘要

The increasing amount of electronic legal documents represents a great opportunityfor the development of intelligent computational systems for legal texts processingand classification. Most of these systems use classical machine learning and largedatasets in English. This paper proposes an approach to automatically predict legalcase outcome from written description of the events in Arabic using deep learning.An in-house corpus from the decisions of the Moroccan Court of Cassation is builtand used to train a deep learning model that predicts judgement. As the created corpusis of limited size, a new data augmentation method is proposed to boost the predictionperformance. Two settings for text representation are tested, namelyFastText and GloVe embeddings, and multiple deep learning models architectures aretested. The proposed approach succeeds in predicting judicial decisions of theMoroccan Court of Cassation with an accuracy of 80.51% on six classes. Even with asmall dataset, the proposed data augmentation method was helpful in improving theoverall models' performance. Despite the advancement in the area of legal judgementprediction over the years, this work is the first attempt to predict legal outcome usingthe documents of the Moroccan Cassation court. The corpus created in the contextof this work will be made publicly available to the community.

著录项

获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号