Classifying long legal documents using short random chunks

📝 Original Info

• Title: Classifying long legal documents using short random chunks
• ArXiv ID: 2512.24997
• Date: 2025-12-31
• Authors: Luis Adrián Cabrera-Diego

📝 Abstract

Classifying legal documents is a challenge, besides their specialized vocabulary, sometimes they can be very long. This means that feeding full documents to a Transformers-based models for classification might be impossible, expensive or slow. Thus, we present a legal document classifier based on DeBERTa V3 and a LSTM, that uses as input a collection of 48 randomlyselected short chunks (max 128 tokens). Besides, we present its deployment pipeline using Temporal, a durable execution solution, which allow us to have a reliable and robust processing workflow. The best model had a weighted F-score of 0.898, while the pipeline running on CPU had a processing median time of 498 seconds per 100 files.

📄 Full Content

...(본문 내용이 길어 생략되었습니다. 사이트에서 전문을 확인해 주세요.)