Automated Metamorphic Testing using Transitive Relations for Specializing Stance Detection Models

Abstract

In machine learning-based natural language processing, methods with high accuracy have been proposed in stance detection tasks.However, when they are applied to specific domains, they are often inaccurate due to domain-specific expressions.We propose an automated metamorphic testing method using transitive relations for creating training data that specializes stance detection in a specific domain.By specializing IBM Debater's stance detection in the currency exchange domain, we confirmed our proposed method can improve the accuracy of judging the currency exchange-related sentences.