ChronosLex: Time-aware Incremental Training for Temporal Generalization of Legal Classification Tasks
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911884894011392 |
|---|---|
| author | Santosh, T. Y. S. S Vuong, Tuan-Quang Grabmair, Matthias |
| author_facet | Santosh, T. Y. S. S Vuong, Tuan-Quang Grabmair, Matthias |
| contents | This study investigates the challenges posed by the dynamic nature of legal multi-label text classification tasks, where legal concepts evolve over time. Existing models often overlook the temporal dimension in their training process, leading to suboptimal performance of those models over time, as they treat training data as a single homogeneous block. To address this, we introduce ChronosLex, an incremental training paradigm that trains models on chronological splits, preserving the temporal order of the data. However, this incremental approach raises concerns about overfitting to recent data, prompting an assessment of mitigation strategies using continual learning and temporal invariant methods. Our experimental results over six legal multi-label text classification datasets reveal that continual learning methods prove effective in preventing overfitting thereby enhancing temporal generalizability, while temporal invariant methods struggle to capture these dynamics of temporal shifts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_14211 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ChronosLex: Time-aware Incremental Training for Temporal Generalization of Legal Classification Tasks Santosh, T. Y. S. S Vuong, Tuan-Quang Grabmair, Matthias Computation and Language This study investigates the challenges posed by the dynamic nature of legal multi-label text classification tasks, where legal concepts evolve over time. Existing models often overlook the temporal dimension in their training process, leading to suboptimal performance of those models over time, as they treat training data as a single homogeneous block. To address this, we introduce ChronosLex, an incremental training paradigm that trains models on chronological splits, preserving the temporal order of the data. However, this incremental approach raises concerns about overfitting to recent data, prompting an assessment of mitigation strategies using continual learning and temporal invariant methods. Our experimental results over six legal multi-label text classification datasets reveal that continual learning methods prove effective in preventing overfitting thereby enhancing temporal generalizability, while temporal invariant methods struggle to capture these dynamics of temporal shifts. |
| title | ChronosLex: Time-aware Incremental Training for Temporal Generalization of Legal Classification Tasks |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2405.14211 |