uOttawa at LegalLens-2024: Transformer-based Classification Experiments

TL;DR

This paper details the uOttawa team's approach using transformer models like RoBERTa for legal text classification tasks in the LegalLens-2024 shared challenge, achieving high accuracy in identifying legal entities and inferences.

Contribution

The paper introduces a transformer-based methodology for legal violation detection, combining spaCy and RoBERTa-CNN models, with publicly available source code.

Findings

86.3% accuracy in Legal NER

88.25% accuracy in Legal NLI

Effective use of transformers in legal NLP tasks

Abstract

This paper presents the methods used for LegalLens-2024 shared task, which focused on detecting legal violations within unstructured textual data and associating these violations with potentially affected individuals. The shared task included two subtasks: A) Legal Named Entity Recognition (L-NER) and B) Legal Natural Language Inference (L-NLI). For subtask A, we utilized the spaCy library, while for subtask B, we employed a combined model incorporating RoBERTa and CNN. Our results were 86.3% in the L-NER subtask and 88.25% in the L-NLI subtask. Overall, our paper demonstrates the effectiveness of transformer models in addressing complex tasks in the legal domain. The source code for our implementation is publicly available at https://github.com/NimaMeghdadi/uOttawa-at-LegalLens-2024-Transformer-based-Classification