"Sharks are not the threat humans are": Argument Component Segmentation in School Student Essays

TL;DR

This paper explores token-level classification methods, especially BERT-based models, for segmenting argument components in middle school essays, improving argument mining accuracy.

Contribution

It introduces a novel BERT-based multi-task learning approach for argument component segmentation in student essays, outperforming previous models.

Findings

BERT-based models achieve the highest accuracy in argument segmentation.

Multi-task learning improves token and sentence classification performance.

The approach is effective on a new corpus of middle school essays.

Abstract

Argument mining is often addressed by a pipeline method where segmentation of text into argumentative units is conducted first and proceeded by an argument component identification task. In this research, we apply a token-level classification to identify claim and premise tokens from a new corpus of argumentative essays written by middle school students. To this end, we compare a variety of state-of-the-art models such as discrete features and deep learning architectures (e.g., BiLSTM networks and BERT-based architectures) to identify the argument components. We demonstrate that a BERT-based multi-task learning architecture (i.e., token and sentence level classification) adaptively pretrained on a relevant unlabeled dataset obtains the best results