DMON: A Simple yet Effective Approach for Argument Structure Learning

TL;DR

DMON is a neural network model that effectively predicts argument relations across various domains by capturing contextual information, outperforming existing models in argument structure learning tasks.

Contribution

The paper introduces DMON, a simple yet effective dual-tower multi-scale convolutional neural network for argument structure learning, demonstrating superior performance across multiple datasets.

Findings

Outperforms state-of-the-art models on three datasets

Effectively captures relations with contextual arguments

Applicable across diverse domains

Abstract

Argument structure learning~(ASL) entails predicting relations between arguments. Because it can structure a document to facilitate its understanding, it has been widely applied in many fields~(medical, commercial, and scientific domains). Despite its broad utilization, ASL remains a challenging task because it involves examining the complex relationships between the sentences in a potentially unstructured discourse. To resolve this problem, we have developed a simple yet effective approach called Dual-tower Multi-scale cOnvolution neural Network~(DMON) for the ASL task. Specifically, we organize arguments into a relationship matrix that together with the argument embeddings forms a relationship tensor and design a mechanism to capture relations with contextual arguments. Experimental results on three different-domain argument mining datasets demonstrate that our framework outperforms state-of-the-art models. The code is available at https://github.com/VRCMF/DMON.git .