Here's My Point: Joint Pointer Architecture for Argument Mining

TL;DR

This paper introduces a neural network-based joint pointer architecture for argument mining that simultaneously extracts argument links and classifies argument component types, achieving state-of-the-art results.

Contribution

It presents the first neural joint model using Pointer Networks for argument structure extraction and component classification, improving performance over previous methods.

Findings

Achieved state-of-the-art results on two corpora.

Joint learning of link extraction and component classification improves accuracy.

Adding a fully-connected layer before the RNN is crucial for performance.

Abstract

One of the major goals in automated argumentation mining is to uncover the argument structure present in argumentative text. In order to determine this structure, one must understand how different individual components of the overall argument are linked. General consensus in this field dictates that the argument components form a hierarchy of persuasion, which manifests itself in a tree structure. This work provides the first neural network-based approach to argumentation mining, focusing on the two tasks of extracting links between argument components, and classifying types of argument components. In order to solve this problem, we propose to use a joint model that is based on a Pointer Network architecture. A Pointer Network is appealing for this task for the following reasons: 1) It takes into account the sequential nature of argument components; 2) By construction, it enforces certain properties of the tree structure present in argument relations; 3) The hidden representations can be applied to auxiliary tasks. In order to extend the contribution of the original Pointer Network model, we construct a joint model that simultaneously attempts to learn the type of argument component, as well as continuing to predict links between argument components. The proposed joint model achieves state-of-the-art results on two separate evaluation corpora, achieving far superior performance than a regular Pointer Network model. Our results show that optimizing for both tasks, and adding a fully-connected layer prior to recurrent neural network input, is crucial for high performance.