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

  title={Label-enhanced Prototypical Network with Contrastive Learning for Multi-label Few-shot Aspect Category Detection},
  author={Han Liu and Feng Zhang and Xiaotong Zhang and Siyang Zhao and Ju Sun and Hong Yu and Xianchao Zhang},
  journal={Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
  • Han Liu, Feng Zhang, Xianchao Zhang
  • Published 14 June 2022
  • Computer Science
  • Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
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… 
1 Citations

Figures and Tables from this paper



Multi-Label Few-Shot Learning for Aspect Category Detection

A multi-label few-shot learning method based on the prototypical network for aspect category detection that significantly outperforms strong baselines and also learns a dynamic threshold per instance by a policy network.

Multi-label Few-shot Learning for Sound Event Recognition

A One-vs.-Rest episode selection strategy is proposed to mitigate the issue of the complexity of forming an episode and apply the strategy to the multi-label few-shot problem.

Hybrid Attention-Based Prototypical Networks for Noisy Few-Shot Relation Classification

This paper designs instancelevel and feature-level attention schemes based on prototypical networks to highlight the crucial instances and features respectively, which significantly enhances the performance and robustness of RC models in a noisy FSL scenario.

MNCN: A Multilingual Ngram-Based Convolutional Network for Aspect Category Detection in Online Reviews

This paper proposes a multilingual method to perform aspect category detection on reviews in different languages, which makes use of a deep convolutional neural network with multilingual word embeddings and is the first attempt at performing aspect category Detection on multiple languages simultaneously.

Few-Shot Text Classification with Induction Network

A novel Induction Network is proposed to learn generalized class-wise representations in few-shot text classification, innovatively combining the dynamic routing algorithm with the typical meta learning framework, and is able to induce from particularity to university, which is a more human-like learning approach.

Few-shot Learning for Multi-label Intent Detection

The proposed model significantly outperforms strong baselines in both one-shot and five-shot settings and introduces label name embedding as anchor points in representation space, which refines representations of different classes to be well-separated from each other.

Few-shot Intent Classification and Slot Filling with Retrieved Examples

This paper proposes a span-level retrieval method that learns similar contextualized representations for spans with the same label via a novel batch-softmax objective and uses the labels of the retrieved spans to construct the final structure with the highest aggregated score.

LaSO: Label-Set Operations Networks for Multi-Label Few-Shot Learning

This work proposes a novel technique for synthesizing samples with multiple labels for the (yet unhandled) multi-label few-shot classification scenario, and proposes to combine pairs of given examples in feature space so that the resulting synthesized feature vectors will correspond to examples whose label sets are obtained through certain set operations on the label sets of the corresponding input pairs.

FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation

Empirical results show that even the most competitive few- shot learning models struggle on this task, especially as compared with humans, and indicate that few-shot relation classification remains an open problem and still requires further research.

Aspect Category Detection via Topic-Attention Network

This paper proposes a deep neural network method based on attention mechanism to identify different aspect categories of a given review sentence, enabling it to attend to different parts of a review sentence based on different topics.