Classifying legal norms with active machine learning

Bernhard Waltl, Johannes Muhr, Ingo Glaser, Georg Bonczek, Elena Scepankova, Florian Matthes

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

28 Scopus citations

Abstract

This paper describes an extended machine learning approach to classify legal norms in German statutory texts. We implemented an active machine learning (AML) framework based on open-source software. Within the paper we discuss different query strategies to optimize the selection of instances during the learning phase to decrease the required training data. The approach was evaluated within the domain of tenancy law. Thereby, we manually labeled the 532 sentences into eight different functional types and achieved an average F1 score of 0.74. Comparing three different classifiers and four query strategies the classification performance F1 varies from 0.60 to 0.93. We could show that in norm classification tasks AML is more efficient than conventional supervised machine learning approaches.

Original languageEnglish
Title of host publicationLegal Knowledge and Information Systems - JURIX 2017
Subtitle of host publicationThe 30th Annual Conference
EditorsAdam Wyner, Giovanni Casini
PublisherIOS Press BV
Pages11-20
Number of pages10
ISBN (Electronic)9781614998372
DOIs
StatePublished - 2017
Event30th International Conference on Legal Knowledge and Information Systems, JURIX 2017 - Luxembourg, Luxembourg
Duration: 13 Dec 201715 Dec 2017

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume302
ISSN (Print)0922-6389
ISSN (Electronic)1879-8314

Conference

Conference30th International Conference on Legal Knowledge and Information Systems, JURIX 2017
Country/TerritoryLuxembourg
CityLuxembourg
Period13/12/1715/12/17

Keywords

  • Active machine learning
  • Norm classification
  • Text mining

Fingerprint

Dive into the research topics of 'Classifying legal norms with active machine learning'. Together they form a unique fingerprint.

Cite this