Label-Guided Prompt for Multi-label Few-shot Aspect Category Detection

TL;DR

This paper introduces a label-guided prompt approach for multi-label few-shot aspect category detection, leveraging large language models to generate discriminative category descriptions and improve sentence representations.

Contribution

It proposes a novel label-guided prompt method that enhances sentence and category representations using large language models, outperforming existing methods.

Findings

Achieved 3.86%-4.75% improvement in Macro-F1 score on two datasets.

Outperforms state-of-the-art methods in multi-label few-shot aspect detection.

Utilizes large language models to generate category descriptions for better prototypes.

Abstract

Multi-label few-shot aspect category detection aims at identifying multiple aspect categories from sentences with a limited number of training instances. The representation of sentences and categories is a key issue in this task. Most of current methods extract keywords for the sentence representations and the category representations. Sentences often contain many category-independent words, which leads to suboptimal performance of keyword-based methods. Instead of directly extracting keywords, we propose a label-guided prompt method to represent sentences and categories. To be specific, we design label-specific prompts to represent sentences by combining crucial contextual and semantic information. Further, the label is introduced into a prompt to obtain category descriptions by utilizing a large language model. This kind of category descriptions contain the characteristics of the aspect categories, guiding the construction of discriminative category prototypes. Experimental results on two public datasets show that our method outperforms current state-of-the-art methods with a 3.86% - 4.75% improvement in the Macro-F1 score.