A Two-Phase Approach Towards Identifying Argument Structure in Natural Language

TL;DR

This paper introduces a two-phase method for extracting argument structures from natural language texts, involving relation classification and structure prediction, validated on multiple datasets with superior performance.

Contribution

The paper presents a novel two-phase approach that combines relation classification with structure prediction, utilizing word embeddings and new training strategies for argument structure extraction.

Findings

Word-embedding features significantly improve classification accuracy

The approach outperforms baseline systems on three datasets

Effective relation classification enhances overall argument structure prediction

Abstract

We propose a new approach for extracting argument structure from natural language texts that contain an underlying argument. Our approach comprises of two phases: Score Assignment and Structure Prediction. The Score Assignment phase trains models to classify relations between argument units (Support, Attack or Neutral). To that end, different training strategies have been explored. We identify different linguistic and lexical features for training the classifiers. Through ablation study, we observe that our novel use of word-embedding features is most effective for this task. The Structure Prediction phase makes use of the scores from the Score Assignment phase to arrive at the optimal structure. We perform experiments on three argumentation datasets, namely, AraucariaDB, Debatepedia and Wikipedia. We also propose two baselines and observe that the proposed approach outperforms baseline systems for the final task of Structure Prediction.