Contextual Modulation for Relation-Level Metaphor Identification

TL;DR

This paper introduces a novel neural architecture that improves relation-level metaphor identification by explicitly modeling contextual interactions, achieving state-of-the-art results on benchmark datasets.

Contribution

It presents a new architecture using contextual modulation for relation-level metaphor detection, addressing limitations of previous word-level and implicit models.

Findings

Achieves state-of-the-art results on benchmark datasets.

Effectively models interaction between metaphor components.

Demonstrates general applicability to other textual classification tasks.

Abstract

Identifying metaphors in text is very challenging and requires comprehending the underlying comparison. The automation of this cognitive process has gained wide attention lately. However, the majority of existing approaches concentrate on word-level identification by treating the task as either single-word classification or sequential labelling without explicitly modelling the interaction between the metaphor components. On the other hand, while existing relation-level approaches implicitly model this interaction, they ignore the context where the metaphor occurs. In this work, we address these limitations by introducing a novel architecture for identifying relation-level metaphoric expressions of certain grammatical relations based on contextual modulation. In a methodology inspired by works in visual reasoning, our approach is based on conditioning the neural network computation on the deep contextualised features of the candidate expressions using feature-wise linear modulation. We demonstrate that the proposed architecture achieves state-of-the-art results on benchmark datasets. The proposed methodology is generic and could be applied to other textual classification problems that benefit from contextual interaction.