AI Paper Atlas

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

AAAI 2021 · Label-efficient and robust learning › Semi-supervised learning · approach: Holistic semi-supervised pipelines · 24 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use attention-based lexicons for pseudo-labeling with BERTBERT fine-tuned with 1% labeled data · IMDB reviewaccuracy (%): 79.74 (3.91) -> 84.87 (1.40)Improved
Use attention-based lexicons for pseudo-labeling with BERTBERT fine-tuned with 1% labeled data · AG Newsaccuracy (%): 88.76 (0.18) -> 90.35 (0.26)Improved
Use attention-based lexicons for pseudo-labeling with BERTBERT fine-tuned with 1% labeled data · Yahoo! Answeraccuracy (%): 57.58 (0.65) -> 59.08 (0.76)Improved
Use attention-based lexicons for pseudo-labeling with BERTBERT fine-tuned with 1% labeled data · DBpediaaccuracy (%): 98.01 (0.17) -> 98.66 (0.24)Improved
Add attention-based lexicon pseudo-labeling (ablation)Attention-based LSTM · IMDB reviewaccuracy (%): 75.43 -> 79.00Improved
Add attention-based lexicon pseudo-labeling (ablation)Attention-based LSTM · AG Newsaccuracy (%): 87.70 -> 88.22Improved
Add attention-based lexicon pseudo-labeling (ablation)Attention-based LSTM · Yahoo! Answeraccuracy (%): 50.98 -> 51.97Improved
Add attention-based lexicon pseudo-labeling (ablation)Attention-based LSTM · DBpediaaccuracy (%): 96.25 -> 96.62Improved
Add attention-based lexicon pseudo-labeling (ablation)Attention-based LSTM with 0.2% labeled data · IMDB reviewaccuracy (%): 64.73 -> 69.94Improved
Add attention-based lexicon pseudo-labeling (ablation)Attention-based LSTM with 0.2% labeled data · AG Newsaccuracy (%): 82.50 -> 85.59Improved
Add attention-based lexicon pseudo-labeling (ablation)Attention-based LSTM with 0.2% labeled data · Yahoo! Answeraccuracy (%): 37.92 -> 43.08Improved
Add attention-based lexicon pseudo-labeling (ablation)Attention-based LSTM with 0.2% labeled data · DBpediaaccuracy (%): 85.25 -> 92.76Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy