Jusletter IT

Supporting the Legal Reasoning Process by Classification of Judgments Applying Active Machine Learning

  • Authors: Ingo Glaser / Jörg Landthaler / Florian Matthes
  • Category: Articles
  • Region: Germany
  • Field of law: Advanced Legal Informatics Systems and Applications, LegalTech
  • Collection: Conference proceedings IRIS 2019
  • Citation: Ingo Glaser / Jörg Landthaler / Florian Matthes, Supporting the Legal Reasoning Process by Classification of Judgments Applying Active Machine Learning, in: Jusletter IT 21. February 2019
The digitalization of information is transforming the way we live and creating many new business models. Digitalization is also taking place in the legal domain. Legal documents, such as contracts and general terms and conditions, are produced thousands of times a day due to numerous online contract generators, e-commerce platforms, banks and insurance companies. As a result, computer-aided legal reasoning has become an attractive research area. The purpose of this research is to investigate the applicability of active machine learning and binary legal text classification in order to detect sentences, providing a statement about the ineffectiveness of a clause.

Table of contents

  • 1. Introduction
  • 2. Related Work
  • 3. Legal Knowledge Base
  • 3.1. Civil Cases at the Federal Court of Justice of Germany
  • 3.2. Structure of a Civil Law Judgment
  • 4. Experiment
  • 4.1. Data
  • 4.2. Classification
  • 5. Evaluation
  • 5.1. Performance of different configurations
  • 5.2. Impact for supporting the legal reasoning process
  • 6. Conclusion & Outlook
  • 7. Bibliography

No comments

There are no comments yet

Ihr Kommentar zu diesem Beitrag

AbonnentInnen dieser Zeitschrift können sich an der Diskussion beteiligen. Bitte loggen Sie sich ein, um Kommentare verfassen zu können.