Enhancing Hyperbole and Metaphor Detection with Their Bidirectional Dynamic Interaction and Emotion Knowledge

TL;DR

This paper introduces EmoBi, a novel emotion-guided framework that enhances hyperbole and metaphor detection by modeling their bidirectional interaction and leveraging emotion knowledge, significantly improving accuracy over existing methods.

Contribution

The paper proposes a new emotion-guided detection framework with bidirectional interaction and emotion domain mapping, outperforming state-of-the-art methods on multiple datasets.

Findings

F1 score increased by 28.1% for hyperbole detection on TroFi dataset.

F1 score increased by 23.1% for metaphor detection on HYPO-L dataset.

Outperforms all baseline methods in experiments.

Abstract

Text-based hyperbole and metaphor detection are of great significance for natural language processing (NLP) tasks. However, due to their semantic obscurity and expressive diversity, it is rather challenging to identify them. Existing methods mostly focus on superficial text features, ignoring the associations of hyperbole and metaphor as well as the effect of implicit emotion on perceiving these rhetorical devices. To implement these hypotheses, we propose an emotion-guided hyperbole and metaphor detection framework based on bidirectional dynamic interaction (EmoBi). Firstly, the emotion analysis module deeply mines the emotion connotations behind hyperbole and metaphor. Next, the emotion-based domain mapping module identifies the target and source domains to gain a deeper understanding of the implicit meanings of hyperbole and metaphor. Finally, the bidirectional dynamic interaction module enables the mutual promotion between hyperbole and metaphor. Meanwhile, a verification mechanism is designed to ensure detection accuracy and reliability. Experiments show that EmoBi outperforms all baseline methods on four datasets. Specifically, compared to the current SoTA, the F1 score increased by 28.1% for hyperbole detection on the TroFi dataset and 23.1% for metaphor detection on the HYPO-L dataset. These results, underpinned by in-depth analyses, underscore the effectiveness and potential of our approach for advancing hyperbole and metaphor detection.