No Argument Left Behind: Overlapping Chunks for Faster Processing of Arbitrarily Long Legal Texts

Autor:	Fama, Israel, Bueno, Bárbara, Alcoforado, Alexandre, Ferraz, Thomas Palmeira, Moya, Arnold, Costa, Anna Helena Reali
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language Computer Science - Artificial Intelligence Computer Science - Computers and Society Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: To appear at 15th STIL @ BRACIS'24
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2410.19184 Zobrazit plný text záznamu View this record from Arxiv