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

arXiv: https://arxiv.org/abs/2309.15588 · HTML: https://mlsanity.com/paper/2309.15588/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 27 references that are in the map.
- First posted on arXiv 27 Sep 2023.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [Joint Embedding of Words and Labels for Text Classification](https://mlsanity.com/paper/1805.04174/) (2018)
- [Zero-shot Text Classification With Generative Language Models](https://mlsanity.com/paper/1912.10165/) (2019)
- [Aspect Category Detection via Topic-Attention Network](https://mlsanity.com/paper/1901.01183/) (2019)
- [Multi-Label Few-Shot Learning for Aspect Category Detection](https://mlsanity.com/paper/2105.14174/) (2021)
- [Label-Driven Denoising Framework for Multi-Label Few-Shot Aspect Category Detection](https://mlsanity.com/paper/2210.04220/) (2022)

## Built on by (most cited first, 1 of 1)

- [Label-Guided Prompt for Multi-label Few-shot Aspect Category Detection](https://mlsanity.com/paper/2407.20673/) (2024)

## Abstract (arXiv)

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.