Multi-Task Attentive Residual Networks for Argument Mining

TL;DR

This paper introduces a residual neural network architecture with attention mechanisms for multi-task argument mining, demonstrating competitive performance across diverse datasets without relying on document structure assumptions.

Contribution

It presents a novel residual architecture that combines attention and multi-task learning, offering a general, efficient alternative to more complex models in argument mining.

Findings

Outperforms some state-of-the-art models on multiple datasets

Achieves a good balance between accuracy and computational efficiency

Works effectively across various types of user-generated and scholarly texts

Abstract

We explore the use of residual networks and neural attention for multiple argument mining tasks. We propose a residual architecture that exploits attention, multi-task learning, and makes use of ensemble, without any assumption on document or argument structure. We present an extensive experimental evaluation on five different corpora of user-generated comments, scientific publications, and persuasive essays. Our results show that our approach is a strong competitor against state-of-the-art architectures with a higher computational footprint or corpus-specific design, representing an interesting compromise between generality, performance accuracy and reduced model size.