Explainable Topic-Enhanced Argument Mining from Heterogeneous Sources

TL;DR

This paper introduces an explainable argument mining method that enhances target and sentence-level topic representations using neural topic models and mutual learning, improving performance on benchmark datasets.

Contribution

It proposes a novel approach combining neural topic modeling and mutual learning to better represent target-related subtopics and sentence-level topics in argument mining.

Findings

Outperforms state-of-the-art baselines in in-target and cross-target settings.

Effectively captures diverse target subtopics and sentence-level topics.

Demonstrates improved interpretability of argument mining results.

Abstract

Given a controversial target such as ``nuclear energy'', argument mining aims to identify the argumentative text from heterogeneous sources. Current approaches focus on exploring better ways of integrating the target-associated semantic information with the argumentative text. Despite their empirical successes, two issues remain unsolved: (i) a target is represented by a word or a phrase, which is insufficient to cover a diverse set of target-related subtopics; (ii) the sentence-level topic information within an argument, which we believe is crucial for argument mining, is ignored. To tackle the above issues, we propose a novel explainable topic-enhanced argument mining approach. Specifically, with the use of the neural topic model and the language model, the target information is augmented by explainable topic representations. Moreover, the sentence-level topic information within the argument is captured by minimizing the distance between its latent topic distribution and its semantic representation through mutual learning. Experiments have been conducted on the benchmark dataset in both the in-target setting and the cross-target setting. Results demonstrate the superiority of the proposed model against the state-of-the-art baselines.