ContrastWSD: Enhancing Metaphor Detection with Word Sense Disambiguation Following the Metaphor Identification Procedure

TL;DR

ContrastWSD is a novel metaphor detection model that combines Word Sense Disambiguation with the Metaphor Identification Procedure, improving accuracy by contrasting contextual and basic word meanings.

Contribution

It introduces a WSD-integrated approach for metaphor detection that surpasses existing methods relying solely on embeddings or external knowledge.

Findings

Outperforms baseline models on benchmark datasets

Effectively distinguishes metaphorical from literal language

Enhances metaphor detection accuracy using sense contrast

Abstract

This paper presents ContrastWSD, a RoBERTa-based metaphor detection model that integrates the Metaphor Identification Procedure (MIP) and Word Sense Disambiguation (WSD) to extract and contrast the contextual meaning with the basic meaning of a word to determine whether it is used metaphorically in a sentence. By utilizing the word senses derived from a WSD model, our model enhances the metaphor detection process and outperforms other methods that rely solely on contextual embeddings or integrate only the basic definitions and other external knowledge. We evaluate our approach on various benchmark datasets and compare it with strong baselines, indicating the effectiveness in advancing metaphor detection.