Research map / Large language models / Language, safety and interpretability
Discourse Level Factors for Sentence Deletion in Text Simplification
Yang Zhong, Chao Jiang, Wei Xu, Junyi Jessy Li
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 sentence embeddings plus Gaussian-binned sparse features in an FNN | Sentence deletion prediction · Newsela elementary | F1 | Improved |
| Use sentence embeddings plus Gaussian-binned sparse features in an FNN | Sentence deletion prediction · Newsela middle | F1 | Improved |
| Add document characteristics to the feature set (ablation) | LR Embed & SF binning · Newsela elementary | F1: 60.0 -> 63.1 | Improved |
| Add position features to the feature set (ablation) | LR Embed & SF binning · Newsela elementary | F1: 60.5 -> 63.1 | Improved |
| Add discourse features to the feature set (ablation) | LR Embed & SF binning · Newsela elementary | F1: 62.9 -> 63.1 | No clear effect |
| Add document characteristics to the feature set (ablation) | LR Embed & SF binning · Newsela middle | F1: 46.1 -> 53.9 | Improved |
| Add position features to the feature set (ablation) | LR Embed & SF binning · Newsela middle | F1: 52.1 -> 53.9 | Improved |
| Add discourse features to the feature set (ablation) | LR Embed & SF binning · Newsela middle | F1: 53.9 -> 53.9 | No clear effect |
| Add Gaussian binning to sparse features | LR with all sparse features · Newsela elementary | F1: 55.3 -> 62.7 | Improved |
| Add Gaussian binning to sparse features | LR with all sparse features · Newsela middle | F1: 57.4 -> 55.4 | Hurt |
| Use embeddings of the two neighboring sentences as additional features | Sentence deletion prediction · Newsela middle | F1 | Hurt |
| Use embeddings of the two neighboring sentences as additional features | Sentence deletion prediction · Newsela elementary | F1 | No clear effect |
Closest papers by meaning
- Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection (AAAI 2025 · similarity 0.82)
- LatestEval: Addressing Data Contamination in Language Model Evaluation through Dynamic and Time-Sensitive Test Construction (AAAI 2024 · similarity 0.82)
- BBScore: A Brownian Bridge Based Metric for Assessing Text Coherence (AAAI 2024 · similarity 0.82)
- TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization (NeurIPS 2026 · similarity 0.82)
- DenoSent: A Denoising Objective for Self-Supervised Sentence Representation Learning (AAAI 2024 · similarity 0.82)
- What's In My Big Data? (ICLR 2024 · similarity 0.82)
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.
