Label-enhanced Prototypical Network with Contrastive Learning for Multi-label Few-shot Aspect Category Detection

TL;DR

This paper introduces a label-enhanced prototypical network with contrastive learning for multi-label few-shot aspect category detection, effectively leveraging label descriptions and contrastive loss to improve prototype discrimination and handle multiple aspect labels.

Contribution

It proposes a novel LPN model that uses label descriptions and contrastive learning to enhance multi-label few-shot aspect detection, achieving state-of-the-art results.

Findings

LPN outperforms existing methods on three datasets.

Incorporating label descriptions improves prototype quality.

Contrastive learning enhances multi-label classification accuracy.

Abstract

Multi-label aspect category detection allows a given review sentence to contain multiple aspect categories, which is shown to be more practical in sentiment analysis and attracting increasing attention. As annotating large amounts of data is time-consuming and labor-intensive, data scarcity occurs frequently in real-world scenarios, which motivates multi-label few-shot aspect category detection. However, research on this problem is still in infancy and few methods are available. In this paper, we propose a novel label-enhanced prototypical network (LPN) for multi-label few-shot aspect category detection. The highlights of LPN can be summarized as follows. First, it leverages label description as auxiliary knowledge to learn more discriminative prototypes, which can retain aspect-relevant information while eliminating the harmful effect caused by irrelevant aspects. Second, it integrates with contrastive learning, which encourages that the sentences with the same aspect label are pulled together in embedding space while simultaneously pushing apart the sentences with different aspect labels. In addition, it introduces an adaptive multi-label inference module to predict the aspect count in the sentence, which is simple yet effective. Extensive experimental results on three datasets demonstrate that our proposed model LPN can consistently achieve state-of-the-art performance.