Automatic detection of arguments in legal texts

TLDR

The study represents an initial effort to automatically classify arguments in legal texts by rhetorical type and to visualize them for easier access and search. The authors framed argument detection as a classification task, training a classifier on annotated arguments and evaluating lexical, syntactic, semantic, and discourse feature sets. Experiments demonstrate the feasibility of detecting arguments in legal texts, yielding measurable results for the proposed classification approach.

Abstract

This paper provides the results of experiments on the detection of arguments in texts among which are legal texts. The detection is seen as a classification problem. A classifier is trained on a set of annotated arguments. Different feature sets are evaluated involving lexical, syntactic, semantic and discourse properties of the texts. The experiments are a first step in the context of automatically classifying arguments in legal texts according to their rhetorical type and their visualization for convenient access and search.