Active Learning for Argument Strength Estimation

TL;DR

This paper investigates the effectiveness of uncertainty-based active learning methods for argument strength estimation, finding that they do not outperform random sampling in sample efficiency on two datasets.

Contribution

The study provides an empirical evaluation of active learning methods in argument mining, highlighting their limitations in current datasets.

Findings

Uncertainty-based AL methods do not outperform random sampling.

Sample-efficient learning remains challenging in argument strength estimation.

Empirical results suggest need for improved AL strategies.

Abstract

High-quality arguments are an essential part of decision-making. Automatically predicting the quality of an argument is a complex task that recently got much attention in argument mining. However, the annotation effort for this task is exceptionally high. Therefore, we test uncertainty-based active learning (AL) methods on two popular argument-strength data sets to estimate whether sample-efficient learning can be enabled. Our extensive empirical evaluation shows that uncertainty-based acquisition functions can not surpass the accuracy reached with the random acquisition on these data sets.