In a context where the Brazilian judiciary system, the largest in the world, faces a crisis due to the slow processing of millions of cases, it becomes imperative to develop efficient methods for analyzing legal texts. We introduce uBERT, a hybrid model that combines Transformer and Recurrent Neural Network architectures to effectively handle long legal texts. Our approach processes the full text regardless of its length while maintaining reasonable computational overhead. Our experiments demonstrate that uBERT achieves superior performance compared to BERT+LSTM when overlapping input is used and is significantly faster than ULMFiT for processing long legal documents.
@article{arxiv.2410.19184,
title = {No Argument Left Behind: Overlapping Chunks for Faster Processing of Arbitrarily Long Legal Texts},
author = {Israel Fama and Bárbara Bueno and Alexandre Alcoforado and Thomas Palmeira Ferraz and Arnold Moya and Anna Helena Reali Costa},
journal= {arXiv preprint arXiv:2410.19184},
year = {2024}
}
Comments
Presented at 15th Symposium in Information and Human Language Technology (STIL) @ BRACIS'24