Grasping the Finer Point: A Supervised Similarity Network for Metaphor Detection

TL;DR

This paper introduces a deep learning model for metaphor detection that surpasses previous methods, addressing the challenge of capturing metaphorical language without relying on hand-engineered features.

Contribution

The paper presents the first deep learning architecture specifically designed for metaphorical composition detection, improving over existing approaches.

Findings

Outperforms existing metaphor detection methods

Demonstrates effectiveness of deep learning for metaphor understanding

Reduces reliance on hand-engineered features

Abstract

The ubiquity of metaphor in our everyday communication makes it an important problem for natural language understanding. Yet, the majority of metaphor processing systems to date rely on hand-engineered features and there is still no consensus in the field as to which features are optimal for this task. In this paper, we present the first deep learning architecture designed to capture metaphorical composition. Our results demonstrate that it outperforms the existing approaches in the metaphor identification task.