An information extraction framework for legal documents: A case study of Thai Supreme Court verdicts
- 1 July 2015
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
A summary judgement of Thai Supreme Court's case is necessary for legal research. Unfortunately, among thousands of decisions, judges traditionally spend a couple of months to manually create just one of them. In this paper, we present a system called “JudgeDoll, ” which automatically extracts the gist information and provides a legal summary of the full judgement. This system can help the judge to rapidly summarize points of law with correct and reliable results. The experiment was conducted on the data set of Thai Supreme Court's cases, particularly about civil and criminal. For the information extraction part, the results showed that our system achieves more than 90% of accuracy in terms of F 1 . For the legal-case summarization part, experts evaluated that they are very satisfied with the summary provided by our system. Furthermore, it requires just only few minutes to process each legal case.Keywords
This publication has 4 references indexed in Scilit:
- An Automatic System for Summarization and Information Extraction of Legal InformationLecture Notes in Computer Science, 2010
- Information extraction from legal documentsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Information Extraction from Thai Text with Unknown Phrase BoundariesLecture Notes in Computer Science, 2009
- Measuring nominal scale agreement among many raters.Psychological Bulletin, 1971