Information Extraction for Planning Court Cases

AbstractLegal documents are often long and unstructured, making them challenging and time-consuming to apprehend. An automatic system that can identify relevant entities and labels within legal documents, would significantly reduce the legal research time. We developed a system to streamline legal case analysis from planning courts by extracting key information from XML files using Named Entity Recognition (NER) and multi-label classification models to convert them into structured form. This research contributes three novel datasets for the Planning Court cases: a NER dataset, a multi-label dataset fully annotated by humans, and newly re-annotated multi-label datasets partially annotated using LLMs. We experimented with various general-purpose and legal domain-specific models with different maximum sequence lengths. It was noted that incorporating paragraph position information improved the performance of models for the multi-label classification task. Our research highlighted the importance of domain-specific models, with LegalRoBERTa and LexLM demonstrating the best performance.