Multi-granularity Argument Mining in Legal Texts

TL;DR

This paper introduces a token-level approach to legal argument mining using a Longformer model, demonstrating improved accuracy and flexibility over traditional sentence-level methods in analyzing legal texts.

Contribution

It presents a novel token-level classification framework for legal argument mining, enhancing accuracy and interpretability compared to prior sentence-level approaches.

Findings

Token-level classification outperforms sentence-level in identifying legal argument elements.

Using Longformer improves model's ability to handle long legal texts.

Token-level approach offers better insights into model focus areas.

Abstract

In this paper, we explore legal argument mining using multiple levels of granularity. Argument mining has usually been conceptualized as a sentence classification problem. In this work, we conceptualize argument mining as a token-level (i.e., word-level) classification problem. We use a Longformer model to classify the tokens. Results show that token-level text classification identifies certain legal argument elements more accurately than sentence-level text classification. Token-level classification also provides greater flexibility to analyze legal texts and to gain more insight into what the model focuses on when processing a large amount of input data.