Research map / Label-efficient and robust learning / Semi-supervised learning
SALNet: Semi-supervised Few-Shot Text Classification with Attention-based Lexicon Construction
Ju-Hyoung Lee, Sang-Ki Ko, Yo-Sub Han
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use attention-based lexicons for pseudo-labeling with BERT | BERT fine-tuned with 1% labeled data · IMDB review | accuracy (%): 79.74 (3.91) -> 84.87 (1.40) | Improved |
| Use attention-based lexicons for pseudo-labeling with BERT | BERT fine-tuned with 1% labeled data · AG News | accuracy (%): 88.76 (0.18) -> 90.35 (0.26) | Improved |
| Use attention-based lexicons for pseudo-labeling with BERT | BERT fine-tuned with 1% labeled data · Yahoo! Answer | accuracy (%): 57.58 (0.65) -> 59.08 (0.76) | Improved |
| Use attention-based lexicons for pseudo-labeling with BERT | BERT fine-tuned with 1% labeled data · DBpedia | accuracy (%): 98.01 (0.17) -> 98.66 (0.24) | Improved |
| Add attention-based lexicon pseudo-labeling (ablation) | Attention-based LSTM · IMDB review | accuracy (%): 75.43 -> 79.00 | Improved |
| Add attention-based lexicon pseudo-labeling (ablation) | Attention-based LSTM · AG News | accuracy (%): 87.70 -> 88.22 | Improved |
| Add attention-based lexicon pseudo-labeling (ablation) | Attention-based LSTM · Yahoo! Answer | accuracy (%): 50.98 -> 51.97 | Improved |
| Add attention-based lexicon pseudo-labeling (ablation) | Attention-based LSTM · DBpedia | accuracy (%): 96.25 -> 96.62 | Improved |
| Add attention-based lexicon pseudo-labeling (ablation) | Attention-based LSTM with 0.2% labeled data · IMDB review | accuracy (%): 64.73 -> 69.94 | Improved |
| Add attention-based lexicon pseudo-labeling (ablation) | Attention-based LSTM with 0.2% labeled data · AG News | accuracy (%): 82.50 -> 85.59 | Improved |
| Add attention-based lexicon pseudo-labeling (ablation) | Attention-based LSTM with 0.2% labeled data · Yahoo! Answer | accuracy (%): 37.92 -> 43.08 | Improved |
| Add attention-based lexicon pseudo-labeling (ablation) | Attention-based LSTM with 0.2% labeled data · DBpedia | accuracy (%): 85.25 -> 92.76 | Improved |
Closest papers by meaning
- ALP: Data Augmentation Using Lexicalized PCFGs for Few-Shot Text Classification (AAAI 2022 · similarity 0.87)
- Few-shot Text Classification with Distributional Signatures (ICLR 2020 · similarity 0.87)
- Learning to Self-Train for Semi-Supervised Few-Shot Classification (NeurIPS 2019 · similarity 0.87)
- Liberating Seen Classes: Boosting Few-Shot and Zero-Shot Text Classification via Anchor Generation and Classification Reframing (AAAI 2024 · similarity 0.85)
- Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphs (AAAI 2025 · similarity 0.84)
- Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning (CVPR 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
