Research Center for Digital Sustainability

Knowledge Graph Construction from Swiss Big Data

Knowledge Graph Construction from Swiss Big Data

This project is available as a Seminar or Bachelor's project.

Introduction

Swiss court decisions are anonymized to protect the privacy of the involved people (parties, victims, etc.). Previous research [1] has shown that it is possible to re-identify companies involved in court decisions by linking the rulings with external data in certain cases. Our project tries to further build an automated system for re-identifying involved people from court rulings. This system can then be used as a test for the anonymization practice of Swiss courts. For more information regarding the overarching research project, please go here.

We propose to approach the general problem of re-identification (not only for a specific domain) with knowledge graphs (ontologies). In this project, you will construct knowledge graphs from both Swiss newspaper articles and court decisions. 

Research Questions

So far, to the best of our knowledge, no one has built a knowledge graph from Swiss newspaper articles or court decisions.

RQ1: How can we build a knowledge graph from large text files?

Steps

  1. Construct a knowledge graph from newspaper articles (data is already available)
  2. Construct a knowledge graph from court decisions (data is already available)
  3. Analyze the quality of the knowledge graph

Activities

⬤⬤⬤◯◯ Programming

⬤⬤⬤⬤◯ Experimentation

⬤◯◯◯◯ Literature

Prerequisites

Good programming skills (preferably in Python)

Preferably experience in deep learning (transformers)

Contact

Joel Niklaus

References

[1] Vokinger, K.N., Mühlematter, U.J., 2019. Re-Identifikation von Gerichtsurteilen durch «Linkage» von Daten(banken). Jusletter 27.
[2] Iyer, Vivek, Arvind Agarwal and Harshit Kumar. “VeeAlign: a supervised deep learning approach to ontology alignment.” OM@ISWC (2020).