Chinese Metaphor Recognition Using a Multi-stage Prompting Large Language Model

TL;DR

This paper introduces a multi-stage prompting framework using Large Language Models to improve Chinese metaphor recognition, especially for cases where tenors or vehicles are not explicitly included, achieving top performance in a shared task.

Contribution

It proposes a novel multi-stage heuristic-enhanced prompt framework that effectively enhances LLMs' ability to recognize Chinese metaphors and their components.

Findings

Achieved top rankings in NLPCC-2024 Shared Task 9.

Enhanced metaphor recognition accuracy with the proposed framework.

Demonstrated effectiveness in identifying tenors, vehicles, and grounds in Chinese metaphors.

Abstract

Metaphors are common in everyday language, and the identification and understanding of metaphors are facilitated by models to achieve a better understanding of the text. Metaphors are mainly identified and generated by pre-trained models in existing research, but situations, where tenors or vehicles are not included in the metaphor, cannot be handled. The problem can be effectively solved by using Large Language Models (LLMs), but significant room for exploration remains in this early-stage research area. A multi-stage generative heuristic-enhanced prompt framework is proposed in this study to enhance the ability of LLMs to recognize tenors, vehicles, and grounds in Chinese metaphors. In the first stage, a small model is trained to obtain the required confidence score for answer candidate generation. In the second stage, questions are clustered and sampled according to specific rules. Finally, the heuristic-enhanced prompt needed is formed by combining the generated answer candidates and demonstrations. The proposed model achieved 3rd place in Track 1 of Subtask 1, 1st place in Track 2 of Subtask 1, and 1st place in both tracks of Subtask 2 at the NLPCC-2024 Shared Task 9.