Metaphor Detection with Effective Context Denoising

TL;DR

This paper introduces RoPPT, a novel RoBERTa-based model that uses target-oriented parse trees for improved metaphor detection, achieving state-of-the-art results by effectively denoising context information.

Contribution

The paper presents a new model, RoPPT, which incorporates target-oriented parse trees to enhance metaphor detection accuracy over existing methods.

Findings

RoPPT achieves state-of-the-art performance on multiple datasets.

The approach effectively denoises context for better metaphor detection.

Comparison shows superiority over other denoising and pruning methods.

Abstract

We propose a novel RoBERTa-based model, RoPPT, which introduces a target-oriented parse tree structure in metaphor detection. Compared to existing models, RoPPT focuses on semantically relevant information and achieves the state-of-the-art on several main metaphor datasets. We also compare our approach against several popular denoising and pruning methods, demonstrating the effectiveness of our approach in context denoising. Our code and dataset can be found at https://github.com/MajiBear000/RoPPT