Automatic Debate Evaluation with Argumentation Semantics and Natural Language Argument Graph Networks

TL;DR

This paper introduces a hybrid approach combining argumentation semantics, Transformer models, and neural graph networks to automatically evaluate complex argumentative debates, addressing data scarcity issues.

Contribution

It presents a novel hybrid method integrating argumentation theory with neural architectures for automatic debate evaluation, pioneering in natural language argument analysis.

Findings

Promising results demonstrating effectiveness of the approach

Lays groundwork for future natural language argument analysis

Addresses data scarcity in argumentation tasks

Abstract

The lack of annotated data on professional argumentation and complete argumentative debates has led to the oversimplification and the inability of approaching more complex natural language processing tasks. Such is the case of the automatic debate evaluation. In this paper, we propose an original hybrid method to automatically evaluate argumentative debates. For that purpose, we combine concepts from argumentation theory such as argumentation frameworks and semantics, with Transformer-based architectures and neural graph networks. Furthermore, we obtain promising results that lay the basis on an unexplored new instance of the automatic analysis of natural language arguments.