LaiDA: Linguistics-aware In-context Learning with Data Augmentation for Metaphor Components Identification

TL;DR

LaiDA is a novel framework that combines linguistics-aware data augmentation, graph attention networks, and in-context learning with LLMs to improve metaphor components identification, addressing challenges of complexity and context dependency.

Contribution

This work introduces LaiDA, integrating linguistics-aware data augmentation, graph attention encoding, and prompt-based fine-tuning of LLMs for enhanced metaphor component detection.

Findings

LaiDA achieved 2nd place in NLPCC2024 shared task.

The framework effectively leverages linguistics and data augmentation.

LaiDA outperforms baseline models in MCI accuracy.

Abstract

Metaphor Components Identification (MCI) contributes to enhancing machine understanding of metaphors, thereby advancing downstream natural language processing tasks. However, the complexity, diversity, and dependency on context and background knowledge pose significant challenges for MCI. Large language models (LLMs) offer new avenues for accurate comprehension of complex natural language texts due to their strong semantic analysis and extensive commonsense knowledge. In this research, a new LLM-based framework is proposed, named Linguistics-aware In-context Learning with Data Augmentation (LaiDA). Specifically, ChatGPT and supervised fine-tuning are utilized to tailor a high-quality dataset. LaiDA incorporates a simile dataset for pre-training. A graph attention network encoder generates linguistically rich feature representations to retrieve similar examples. Subsequently, LLM is fine-tuned with prompts that integrate linguistically similar examples. LaiDA ranked 2nd in Subtask 2 of NLPCC2024 Shared Task 9, demonstrating its effectiveness. Code and data are available at https://github.com/WXLJZ/LaiDA.