Deep Learning-Based Knowledge Injection for Metaphor Detection: A Comprehensive Review

TL;DR

The paper tackles metaphor detection and investigates how deep learning models can leverage external knowledge to improve detection accuracy. It categorizes knowledge into syntactic, semantic, and emotional signals and maps them to three integration strategies: output modulation, additional inputs, and multi-task learning. It surveys datasets (e.g., the VUA family, TroFi, MOH-X) and evaluation metrics, analyzes strengths and limitations of current approaches, and outlines future directions. The work provides theoretical guidance and practical references to design knowledge-infused metaphor detectors and informs researchers about effective knowledge infusion pathways.

Abstract

Metaphor as an advanced cognitive modality works by extracting familiar concepts in the target domain in order to understand vague and abstract concepts in the source domain. This helps humans to quickly understand and master new domains and thus adapt to changing environments. With the continuous development of metaphor research in the natural language community, many studies using knowledge-assisted models to detect textual metaphors have emerged in recent years. Compared to not using knowledge, systems that introduce various kinds of knowledge achieve greater performance gains and reach SOTA in a recent study. Based on this, the goal of this paper is to provide a comprehensive review of research advances in the application of deep learning for knowledge injection in metaphor detection tasks. We will first systematically summarize and generalize the mainstream knowledge and knowledge injection principles. Then, the datasets, evaluation metrics, and benchmark models used in metaphor detection tasks are examined. Finally, we explore the current issues facing knowledge injection methods and provide an outlook on future research directions.