Mind Your Neighbours: Leveraging Analogous Instances for Rhetorical Role Labeling for Legal Documents
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917628622143488 |
|---|---|
| author | Santosh, T. Y. S. S Sarwat, Hassan Abdou, Ahmed Grabmair, Matthias |
| author_facet | Santosh, T. Y. S. S Sarwat, Hassan Abdou, Ahmed Grabmair, Matthias |
| contents | Rhetorical Role Labeling (RRL) of legal judgments is essential for various tasks, such as case summarization, semantic search and argument mining. However, it presents challenges such as inferring sentence roles from context, interrelated roles, limited annotated data, and label imbalance. This study introduces novel techniques to enhance RRL performance by leveraging knowledge from semantically similar instances (neighbours). We explore inference-based and training-based approaches, achieving remarkable improvements in challenging macro-F1 scores. For inference-based methods, we explore interpolation techniques that bolster label predictions without re-training. While in training-based methods, we integrate prototypical learning with our novel discourse-aware contrastive method that work directly on embedding spaces. Additionally, we assess the cross-domain applicability of our methods, demonstrating their effectiveness in transferring knowledge across diverse legal domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_01344 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Mind Your Neighbours: Leveraging Analogous Instances for Rhetorical Role Labeling for Legal Documents Santosh, T. Y. S. S Sarwat, Hassan Abdou, Ahmed Grabmair, Matthias Computation and Language Rhetorical Role Labeling (RRL) of legal judgments is essential for various tasks, such as case summarization, semantic search and argument mining. However, it presents challenges such as inferring sentence roles from context, interrelated roles, limited annotated data, and label imbalance. This study introduces novel techniques to enhance RRL performance by leveraging knowledge from semantically similar instances (neighbours). We explore inference-based and training-based approaches, achieving remarkable improvements in challenging macro-F1 scores. For inference-based methods, we explore interpolation techniques that bolster label predictions without re-training. While in training-based methods, we integrate prototypical learning with our novel discourse-aware contrastive method that work directly on embedding spaces. Additionally, we assess the cross-domain applicability of our methods, demonstrating their effectiveness in transferring knowledge across diverse legal domains. |
| title | Mind Your Neighbours: Leveraging Analogous Instances for Rhetorical Role Labeling for Legal Documents |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2404.01344 |