Objection management

This project provides ideas for an automatic objection management system. It should be seen as a Proof-of-Concept and gives ideas to others who are tasked with a similar problem. In this project we use simple machine learning models as well as large language models (LLM) to identify and categorize arguments in objections. The detection of duplicates is also briefly discussed. The ideas are demonstrated using real data that was generated during the process of searching for a final repository for nuclear waste in Germany. These are the objections to the interim report of the identification of sub-areas: https://beteiligung.bge.de/