Few-Shot Multi-Label Aspect Category Detection Utilizing Prototypical Network with Sentence-Level Weighting and Label Augmentation

TL;DR

This paper proposes a novel few-shot multi-label aspect category detection method using a prototypical network with sentence-level weighting and label augmentation, improving prototype quality and detection accuracy.

Contribution

It introduces support set attention with augmented label info and sentence-level weighting to better handle instance variation and noise in few-shot multi-label detection.

Findings

Outperforms all baselines on Yelp dataset in four scenarios.

Effective in mitigating noise at word and instance levels.

Enhances prototype computation with weighted averaging and label augmentation.

Abstract

Multi-label aspect category detection is intended to detect multiple aspect categories occurring in a given sentence. Since aspect category detection often suffers from limited datasets and data sparsity, the prototypical network with attention mechanisms has been applied for few-shot aspect category detection. Nevertheless, most of the prototypical networks used so far calculate the prototypes by taking the mean value of all the instances in the support set. This seems to ignore the variations between instances in multi-label aspect category detection. Also, several related works utilize label text information to enhance the attention mechanism. However, the label text information is often short and limited, and not specific enough to discern categories. In this paper, we first introduce support set attention along with the augmented label information to mitigate the noise at word-level for each support set instance. Moreover, we use a sentence-level attention mechanism that gives different weights to each instance in the support set in order to compute prototypes by weighted averaging. Finally, the calculated prototypes are further used in conjunction with query instances to compute query attention and thereby eliminate noises from the query set. Experimental results on the Yelp dataset show that our proposed method is useful and outperforms all baselines in four different scenarios.