Sebis Research News

Two papers of SEBIS were nominated for the LexisNexis Best Paper Award at IRIS 2018.

The first paper is about Named Entity Recognition, Extraction, and Linking in German Legal Documents and was written by Ingo Glaser, Benrhard Waltl and Florian Matthes. Please look here for furhter information about this paper.

The second paper from Daniel Braun, Elena Scepankova, Patrick Holl, and Florian Matthes is titled Customer-Centered LegalTech: Automated Analysis of Standard Form Contracts.

Accepted for LexisNexis Best Paper Award

Abstract

A paper has been accepted for publication at the Internationels Symposium on Legal Informatics (IRIS). In the paper entitled LEXIA - A Data Science Environment for Semantic Analysis of German Legal Texts, the author team consisting of Bernhard Waltl, Florian Matthes, Tobias Waltl, and Thomas Grass show how modern technologies of text mining algorithms can be applied to the legal texts. It shows how to consider the particularities of legal texts, such as laws or judgments, in the data model and provides a reference architecture for a collaborative data science environment.

A paper has been accepted for publication at the International Symposium for Legal Informatic. In the paper entitled "Comparison of Law Texts: An Analysis of German and Austrian Legislation regarding Linguistic and Structural Metrics", the author team (Bernhard Waltl and Florian Matthes) discusses the analysis of legal texts regarding to linguistic metrics. Thereby, they extended an existing set of complexity indicators regarding linguistic and structural properties and applied them to Austrian and German laws. Based on the results that were generated, it is possible to formally compare laws and determine inter-subjective insights. See [Wa15a]

A paper has been accepted for publication at the 27th International Conference on Legal Knowledge and Information Systems. In the paper entitled "Towards Measures of Complexity: Applying Structural and Linguistic Metrics to German Laws", the author team (Bernhard Waltl and Florian Matthes) discusses the complexity of legal texts regarding to linguistic metrics. Thereby, they present the result of the analysis of about 3553 German law texts by applying structural and lexical metrics to them. They calculated several structural and lexical indicators for complexity and determined highly significant correlations (p <= 0.01). The papers' contribution is a set of metrics, enabling a structured and objective comparison of legal texts regarding their complexity. See [Wa14c]