Label-Driven Denoising Framework for Multi-Label Few-Shot Aspect Category Detection

TL;DR

This paper introduces a label-driven denoising framework for multi-label few-shot aspect category detection, effectively reducing noise and improving prototype quality by leveraging label information, outperforming existing methods.

Contribution

The paper proposes a novel label-driven denoising framework that addresses noise issues in prototype generation for few-shot aspect detection, enhancing accuracy.

Findings

Outperforms state-of-the-art methods in experiments

Effectively reduces noise in prototype generation

Improves detection accuracy in few-shot scenarios

Abstract

Multi-Label Few-Shot Aspect Category Detection (FS-ACD) is a new sub-task of aspect-based sentiment analysis, which aims to detect aspect categories accurately with limited training instances. Recently, dominant works use the prototypical network to accomplish this task, and employ the attention mechanism to extract keywords of aspect category from the sentences to produce the prototype for each aspect. However, they still suffer from serious noise problems: (1) due to lack of sufficient supervised data, the previous methods easily catch noisy words irrelevant to the current aspect category, which largely affects the quality of the generated prototype; (2) the semantically-close aspect categories usually generate similar prototypes, which are mutually noisy and confuse the classifier seriously. In this paper, we resort to the label information of each aspect to tackle the above problems, along with proposing a novel Label-Driven Denoising Framework (LDF). Extensive experimental results show that our framework achieves better performance than other state-of-the-art methods.