Metaphor Detection using Deep Contextualized Word Embeddings

TL;DR

This paper introduces an end-to-end deep learning approach using contextualized embeddings, LSTMs, and attention for metaphor detection, eliminating the need for handcrafted features and demonstrating strong performance on benchmark datasets.

Contribution

The work presents a novel, fully automated method for metaphor detection that relies solely on raw text inputs, improving applicability and performance over traditional feature-based approaches.

Findings

Outperforms existing baselines on TroFi and MOH-X datasets.

Requires only raw text sequences, simplifying the detection process.

Experimental results confirm the effectiveness of the proposed method.

Abstract

Metaphors are ubiquitous in natural language, and their detection plays an essential role in many natural language processing tasks, such as language understanding, sentiment analysis, etc. Most existing approaches for metaphor detection rely on complex, hand-crafted and fine-tuned feature pipelines, which greatly limit their applicability. In this work, we present an end-to-end method composed of deep contextualized word embeddings, bidirectional LSTMs and multi-head attention mechanism to address the task of automatic metaphor detection. Our method, unlike many other existing approaches, requires only the raw text sequences as input features to detect the metaphoricity of a phrase. We compare the performance of our method against the existing baselines on two benchmark datasets, TroFi, and MOH-X respectively. Experimental evaluations confirm the effectiveness of our approach.