LawStats – Large-Scale German Court Decision Evaluation Using Web Service Classifiers - Machine Learning and Knowledge Extraction Access content directly
Conference Papers Year : 2018

LawStats – Large-Scale German Court Decision Evaluation Using Web Service Classifiers

Eugen Ruppert
  • Function : Author
  • PersonId : 1043671
Dirk Hartung
  • Function : Author
  • PersonId : 1043672
Phillip Sittig
  • Function : Author
  • PersonId : 1043673
Tjorben Gschwander
  • Function : Author
  • PersonId : 1043674
Lennart Rönneburg
  • Function : Author
  • PersonId : 1043675
Tobias Killing
  • Function : Author
  • PersonId : 1043676
Chris Biemann
  • Function : Author
  • PersonId : 1043677


LawStats provides quantitative insights into court decisions from the Bundesgerichtshof - Federal Court of Justice (BGH), the Federal Court of Justice in Germany. Using Watson Web Services and approaches from Sentiment Analysis (SA), we can automatically classify the revision outcome and offer statistics on judges, senates, previous instances etc. via faceted search. These statistics are accessible through a open web interface to aid law professionals. With a clear focus on interpretability, users can not only explore statistics, but can also understand, which sentences in the decision are responsible for the machine’s decision; links to the original texts provide more context. This is the first large-scale application of Machine Learning (ML) based Natural Language Processing (NLP) for German in the analysis of ordinary court decisions in Germany that we are aware of. We have analyzed over 50,000 court decisions and extracted the outcomes and relevant entities. The modular architecture of the application allows continuous improvements of the ML model as more annotations become available over time. The tool can provide a critical foundation for further quantitative research in the legal domain and can be used as a proof-of-concept for similar efforts.
Fichier principal
Vignette du fichier
472936_1_En_14_Chapter.pdf (344.78 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02060039 , version 1 (07-03-2019)





Eugen Ruppert, Dirk Hartung, Phillip Sittig, Tjorben Gschwander, Lennart Rönneburg, et al.. LawStats – Large-Scale German Court Decision Evaluation Using Web Service Classifiers. 2nd International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE), Aug 2018, Hamburg, Germany. pp.212-222, ⟨10.1007/978-3-319-99740-7_14⟩. ⟨hal-02060039⟩
125 View
123 Download



Gmail Facebook X LinkedIn More