Towards Intelligent Legal Document Analysis: CNN-Driven Classification of Case Law Texts

2026-04-19

AI Summary

Legal case documents are characterized by rigid formatting and dense technical terminology, making manual classification inefficient and error-prone. This work proposes a lightweight yet effective framework that integrates lemmatization, subword-aware FastText embeddings, and a multi-kernel one-dimensional convolutional neural network (CNN) to automatically classify citation processing types. With only 5.1 million parameters, the model achieves 97.26% accuracy, 96.82% macro F1-score, and 97.83% AUC-ROC on a dataset of 25,000 annotated documents. Inference takes just 0.31 milliseconds per document—13 times faster than BERT—demonstrating that a thoughtfully designed CNN can serve as a highly efficient alternative to heavyweight Transformer-based models while significantly outperforming established baselines.

Technology Category

• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification

Application Category

• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Legal practitioners and judicial institutions face an ever-growing volume of case-law documents characterised by formalised language, lengthy sentence structures, and highly specialised terminology, making manual triage both time-consuming and error-prone. This work presents a lightweight yet high-accuracy framework for citation-treatment classification that pairs lemmatisation-based preprocessing with subword-aware FastText embeddings and a multi-kernel one-dimensional Convolutional Neural Network (CNN). Evaluated on a publicly available corpus of 25,000 annotated legal documents with a 75/25 training-test partition, the proposed system achieves 97.26% classification accuracy and a macro F1-score of 96.82%, surpassing established baselines including fine-tuned BERT, Long Short-Term Memory (LSTM) with FastText, CNN with random embeddings, and a Term Frequency-Inverse Document Frequency (TF-IDF) k-Nearest Neighbour (KNN) classifier. The model also attains the highest Area Under the Receiver Operating Characteristic (AUC-ROC) curve of 97.83% among all compared systems while operating with only 5.1 million parameters and an inference latency of 0.31 ms per document - more than 13 times faster than BERT. Ablation experiments confirm the individual contribution of each pipeline component, and the confusion matrix reveals that residual errors are confined to semantically adjacent citation categories. These findings indicate that carefully designed convolutional architectures represent a scalable, resource-efficient alternative to heavyweight transformers for intelligent legal document analysis.

Problem

• legal document analysis
• case law classification
• citation-treatment classification
• intelligent legal systems
• legal text processing

Innovation

• CNN
• FastText
• legal document classification
• lemmatisation
• lightweight NLP