Multi-Task Learning Improves Performance In Deep Argument Mining Models

TL;DR

This paper demonstrates that multi-task learning leveraging shared representations significantly enhances the performance of deep argument mining models across various tasks, highlighting the shared semantic structure among them.

Contribution

It introduces a multi-task learning framework that exploits commonalities between argument mining tasks, outperforming existing single-task models.

Findings

Multi-task approach improves argument mining accuracy

Shared representations capture common semantic features

Performance surpasses state-of-the-art models

Abstract

The successful analysis of argumentative techniques from user-generated text is central to many downstream tasks such as political and market analysis. Recent argument mining tools use state-of-the-art deep learning methods to extract and annotate argumentative techniques from various online text corpora, however each task is treated as separate and different bespoke models are fine-tuned for each dataset. We show that different argument mining tasks share common semantic and logical structure by implementing a multi-task approach to argument mining that achieves better performance than state-of-the-art methods for the same problems. Our model builds a shared representation of the input text that is common to all tasks and exploits similarities between tasks in order to further boost performance via parameter-sharing. Our results are important for argument mining as they show that different tasks share substantial similarities and suggest a holistic approach to the extraction of argumentative techniques from text.