Argument Mining as a Text-to-Text Generation Task

TL;DR

This paper introduces a unified text-to-text generation approach for argument mining that simplifies the process by generating argumentative structures directly, achieving state-of-the-art results across multiple datasets.

Contribution

It presents a novel method using a pretrained encoder-decoder model to directly generate argumentative annotations, removing the need for complex subtasks and postprocessing.

Findings

Achieves state-of-the-art performance on three benchmark datasets

Simplifies argument mining by eliminating multiple subtasks

Easily adaptable to various argumentative structures

Abstract

Argument Mining(AM) aims to uncover the argumentative structures within a text. Previous methods require several subtasks, such as span identification, component classification, and relation classification. Consequently, these methods need rule-based postprocessing to derive argumentative structures from the output of each subtask. This approach adds to the complexity of the model and expands the search space of the hyperparameters. To address this difficulty, we propose a simple yet strong method based on a text-to-text generation approach using a pretrained encoder-decoder language model. Our method simultaneously generates argumentatively annotated text for spans, components, and relations, eliminating the need for task-specific postprocessing and hyperparameter tuning. Furthermore, because it is a straightforward text-to-text generation method, we can easily adapt our approach to various types of argumentative structures. Experimental results demonstrate the effectiveness of our method, as it achieves state-of-the-art performance on three different types of benchmark datasets: the Argument-annotated Essays Corpus(AAEC), AbstRCT, and the Cornell eRulemaking Corpus(CDCP)