Multi-Task Learning for Argumentation Mining in Low-Resource Settings

TL;DR

This paper explores how multi-task learning can enhance argumentation mining, especially in low-resource scenarios, by leveraging related tasks to improve performance where data is scarce.

Contribution

It demonstrates that multi-task learning outperforms single-task learning in argument component identification when training data is limited, challenging previous assumptions.

Findings

MTL performs better than single-task learning with limited data

MTL is effective for semantic and higher-level argumentation tasks

Conceptualizations across AM datasets are more aligned than previously thought

Abstract

We investigate whether and where multi-task learning (MTL) can improve performance on NLP problems related to argumentation mining (AM), in particular argument component identification. Our results show that MTL performs particularly well (and better than single-task learning) when little training data is available for the main task, a common scenario in AM. Our findings challenge previous assumptions that conceptualizations across AM datasets are divergent and that MTL is difficult for semantic or higher-level tasks.