Classifying Argumentative Relations Using Logical Mechanisms and Argumentation Schemes

TL;DR

This paper introduces a logical mechanism-based approach to classify argumentative relations, improving interpretability and performance over black-box models by leveraging factual, sentiment, causal, and normative relations.

Contribution

It proposes a novel, theory-informed framework for classifying argumentative relations without relying solely on data-driven training, enhancing both interpretability and accuracy.

Findings

Mechanism-based classification outperforms unsupervised baselines.

Logical mechanisms improve supervised classifier representations.

Approach enhances interpretability of argumentative relation classification.

Abstract

While argument mining has achieved significant success in classifying argumentative relations between statements (support, attack, and neutral), we have a limited computational understanding of logical mechanisms that constitute those relations. Most recent studies rely on black-box models, which are not as linguistically insightful as desired. On the other hand, earlier studies use rather simple lexical features, missing logical relations between statements. To overcome these limitations, our work classifies argumentative relations based on four logical and theory-informed mechanisms between two statements, namely (i) factual consistency, (ii) sentiment coherence, (iii) causal relation, and (iv) normative relation. We demonstrate that our operationalization of these logical mechanisms classifies argumentative relations without directly training on data labeled with the relations, significantly better than several unsupervised baselines. We further demonstrate that these mechanisms also improve supervised classifiers through representation learning.