uOttawa at LegalLens-2024: Transformer-based Classification Experiments

Nima Meghdadi, Diana Inkpen
10/28/2024
cs.CL

Official code: NimaMeghdadi/uOttawa-at-LegalLens-2024-Transformer-based-Classification (0 stars, MIT, last commit 2024-10-29).

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

View on arXivView PDF

Code Implementations(1)

NimaMeghdadi/uOttawa-at-LegalLens-2024-Transformer-based-ClassificationOfficial100%
MIT

This repository contains the code and models for the LegalLens-2024 shared task, which detects legal violations in unstructured text and associates them with affected individuals using transformer models like BERT, RoBERTa, and DeBERTa for Named Entity Recognition (L-NER) and Natural Language Inference (L-NLI).

01Jupyter NotebookJul 13, 20241 years agoMIT
colabdeberta-v3-baselnernernli+3 more

Cite this paper

@article{meghdadi2024uottawa,
  title  = {uOttawa at LegalLens-2024: Transformer-based Classification Experiments},
  author = {Nima Meghdadi and Diana Inkpen},
  year   = {2024},
  eprint = {2410.21139},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.21139v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.21139.svg)](https://codeofpaper.com/paper/2410.21139)

Discussion