Focusing on legal cases: Automatic classification of legal documents with sentence embeddings and deep learning models

Fawaz Khaled Alarfaj · 2026

Read Focusing on legal cases: Automatic classification of legal documents with sentence embeddings and deep learning models by Fawaz Khaled Alarfaj (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0350673.txt.

Description

Fawaz Khaled Alarfaj tested machine and deep learning methods for sorting legal documents into case categories automatically. Courts and firms drown in complex legal text, and hand sorting is slow. Thousands of real legal files were turned into features ranging from word counts to modern sentence embeddings, then fed to many classifiers.

An ensemble of extremely randomised trees scored best at about eighty nine percent accuracy, beating deep models in this test. Pooling many varied trees curbed overfitting on tricky legal language. Reliable auto sorting can speed filing, search, and case triage, though high stakes legal calls still need human review of edge cases.

Catalog record

CREATORFawaz Khaled Alarfaj
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE54854
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0350673

Browse the full library · About the Tower of Babel