EMNLP Findings2022
Label-Driven Denoising Framework for Multi-Label Few-Shot Aspect Category Detection
Abstract
Multi-Label Few-Shot Aspect Category Detection (FS-ACD) is a new sub-task of aspectbased 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 semanticallyclose 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. Our code and datasets are available at https://github.com/1429904852/LDF.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Variational Hybrid-Attention Framework for Multi-Label Few-Shot Aspect Category Detection cites Few-shot Learning for Multi-label Intent Detection
- Variational Hybrid-Attention Framework for Multi-Label Few-Shot Aspect Category Detection cites Multi-Label Few-Shot Learning for Aspect Category Detection
- Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning cites Supervised Contrastive Learning
- Multi-Label Few-Shot Learning for Aspect Category Detection cites Few-shot Learning for Multi-label Intent Detection
Cited by top-tier papers1
Builds on5
- Supervised Contrastive LearningPrannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna et al.NeurIPS 2020 · 7,049 citations
- Supervised Contrastive Learning for Pre-trained Language Model Fine-tuningBeliz Gunel, Jingfei Du, Alexis Conneau, Veselin StoyanovICLR 2021 · 595 citations
- Few-shot Learning for Multi-label Intent DetectionYutai Hou, Yongkui Lai, Yushan Wu, Wanxiang Che et al.AAAI 2021 · 60 citations
- Multi-Label Few-Shot Learning for Aspect Category DetectionMengting Hu, Shiwan Zhao, Honglei Guo, Chao Xue et al.ACL 2021
- Self-Guided Contrastive Learning for BERT Sentence RepresentationsTaeuk Kim, Kang Min Yoo, Sang-goo LeeACL 2021
Related papers
- Label-enhanced Prototypical Network with Contrastive Learning for Multi-label Few-shot Aspect Category DetectionHan Liu, Feng Zhang, Xiaotong Zhang, Siyang Zhao et al.KDD 2022 · 23 citations
- Causal Denoising Prototypical Network for Few-Shot Multi-label Aspect Category DetectionJin Cui, Xinfeng Wang, Yoshimi Suzuki, Fumiyo FukumotoACL Findings 2025
- AX-MABSA: A Framework for Extremely Weakly Supervised Multi-label Aspect Based Sentiment AnalysisSabyasachi Kamila, Walid Magdy, Sourav Dutta, MingXue WangEMNLP 2022 · 5 citations
- Few-shot Joint Multimodal Aspect-Sentiment Analysis Based on Generative Multimodal PromptXiaocui Yang, Shi Feng, Daling Wang, Qi Sun et al.ACL Findings 2023 · 41 citations
- A Self-enhancement Multitask Framework for Unsupervised Aspect Category DetectionThi-Nhung Nguyen, Hoang Ngo, Kiem-Hieu Nguyen, Tuan-Dung CaoEMNLP 2023 · 3 citations
