Multi-Task Attentive Residual Networks for Argument Mining

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.

arXiv comment16 pages, 3 figures

References in corpus (9)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• BioBERT: a pre-trained biomedical language representation model for biomedical text mining
• Natural Language Processing (almost) from Scratch
• Attention in Natural Language Processing
• Argumentation Mining in User-Generated Web Discourse
• The evolution of argumentation mining: From models to social media and emerging tools
• Modeling Content and Context with Deep Relational Learning
• Neural-Symbolic Argumentation Mining: an Argument in Favor of Deep Learning and Reasoning
• Contextual Argument Component Classification for Class Discussions