Enhancing Argument Structure Extraction with Efficient Leverage of Contextual Information

TL;DR

This paper introduces ECASE, a novel model for argument structure extraction that effectively leverages contextual information through a sequence-attention module, distance-weighted loss, and data augmentation, achieving state-of-the-art results.

Contribution

The paper presents a new context-aware ASE model with enhanced modeling capacity and data augmentation techniques, outperforming existing methods.

Findings

Achieves state-of-the-art performance on five datasets

Sequence-attention module improves contextual aggregation

Data augmentation reduces reliance on specific words

Abstract

Argument structure extraction (ASE) aims to identify the discourse structure of arguments within documents. Previous research has demonstrated that contextual information is crucial for developing an effective ASE model. However, we observe that merely concatenating sentences in a contextual window does not fully utilize contextual information and can sometimes lead to excessive attention on less informative sentences. To tackle this challenge, we propose an Efficient Context-aware ASE model (ECASE) that fully exploits contextual information by enhancing modeling capacity and augmenting training data. Specifically, we introduce a sequence-attention module and distance-weighted similarity loss to aggregate contextual information and argumentative information. Additionally, we augment the training data by randomly masking discourse markers and sentences, which reduces the model's reliance on specific words or less informative sentences. Our experiments on five datasets from various domains demonstrate that our model achieves state-of-the-art performance. Furthermore, ablation studies confirm the effectiveness of each module in our model.