The Unreasonable Effectiveness of the Baseline: Discussing SVMs in Legal Text Classification

15 Sep 2021  ·  Benjamin Clavié, Marc Alphonsus ·

We aim to highlight an interesting trend to contribute to the ongoing debate around advances within legal Natural Language Processing. Recently, the focus for most legal text classification tasks has shifted towards large pre-trained deep learning models such as BERT. In this paper, we show that a more traditional approach based on Support Vector Machine classifiers reaches surprisingly competitive performance with BERT-based models on the classification tasks in the LexGLUE benchmark. We also highlight that error reduction obtained by using specialised BERT-based models over baselines is noticeably smaller in the legal domain when compared to general language tasks. We present and discuss three hypotheses as potential explanations for these results to support future discussions.

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Natural Language Understanding LexGLUE Optimised SVM Baseline ECtHR Task A 66.3 / 55.0 # 8
ECtHR Task B 76.0 / 65.4 # 7
SCOTUS 74.4 / 64.5 # 2
EUR-LEX 65.7 / 49.0 # 7
LEDGAR 88.0 / 82.6 # 1

Methods