Research map / Label-efficient and robust learning / Semi-supervised learning
Semi-Supervised Text Simplification with Back-Translation and Asymmetric Denoising Autoencoders
Yanbin Zhao, Lu Chen, Zhi Chen, Kai Yu
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 |
|---|---|---|---|
| add additive noise on simple sentences to MT-style noise (ablation) | BTTS semi-supervised 10% · Newsela | SARI: 33.63 -> 35.94 | Improved |
| add substitution noise on top of additive noise (ablation) | BTTS semi-supervised 10% · Newsela | SARI: 35.94 -> 38.69 | Improved |
| add additive noise to MT-style noise (ablation) | BTTS semi-supervised 10% · WikiLarge | SARI: 35.91 -> 36.85 | Improved |
| add substitution noise on top of additive (ablation) | BTTS semi-supervised 10% · WikiLarge | SARI: 36.85 -> 37.25 | Improved |
| add reinforcement learning rewards (fluency, relevance, complexity) (ablation) | BTTS unsupervised · Newsela | SARI: 37.07 -> 37.69 | Improved |
| add reinforcement learning rewards (ablation) | BTTS unsupervised · WikiLarge | SARI: 36.98 -> 37.06 | No clear effect |
| add 10% parallel data to unsupervised BTTS | BTTS · Newsela | SARI: 37.07 -> 38.69 | Improved |
| use full parallel data instead of 10% | BTTS · Newsela | SARI: 38.69 -> 39.69 | Improved |
| use full parallel data instead of 10% | BTTS · WikiLarge | SARI: 37.25 -> 36.92 | No clear effect |
| add RL to semi-supervised 10% model (ablation) | BTTS(+10%) · Newsela | SARI: 38.69 -> 38.62 | No clear effect |
Closest papers by meaning
- DenoSent: A Denoising Objective for Self-Supervised Sentence Representation Learning (AAAI 2024 · similarity 0.87)
- Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models (ICLR 2024 · similarity 0.86)
- Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning (NeurIPS 2025 · similarity 0.86)
- Pruning Large Language Models with Semi-Structural Adaptive Sparse Training (AAAI 2025 · similarity 0.85)
- AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models (NeurIPS 2024 · similarity 0.85)
- SimReg: Achieving Higher Performance in the Pretraining via Embedding Similarity Regularization (NeurIPS 2026 · similarity 0.85)
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.
