HARGAN: Heterogeneous Argument Attention Network for Persuasiveness Prediction
Journal
35th AAAI Conference on Artificial Intelligence, AAAI 2021
Journal Volume
14B
ISBN
9781713835974
Date Issued
2021-01-01
Author(s)
Abstract
Argument structure elaborates the relation among claims and premises. Previous works in persuasiveness prediction seldom consider this relation in their architectures. To take argument structure information into account, this paper proposes an approach to persuasiveness prediction with a novel graphbased neural network model, called heterogeneous argument attention network (HARGAN). By jointly training on the persuasiveness and stance of the replies, our model achieves the state-of-the-art performance on the ChangeMyView (CMV) dataset for the persuasiveness prediction task. Experimental results show that the graph setting enables our model to aggregate information across multiple paragraphs effectively. In the meanwhile, our stance prediction auxiliary task enables our model to identify the viewpoint of each party, and helps our model perform better on the persuasiveness prediction. & copy; 2021, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
Type
conference paper