Research map / Image generation / Text-to-image diffusion
Learning to Select Bi-Aspect Information for Document-Scale Text Content Manipulation
Xiaocheng Feng, Yawei Sun, Bing Qin, Heng Gong, Yibo Sun, Wei Bi, XiaoJiang Liu, Ting Liu
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 interactive attention to jointly relate records and reference words (ablation) | Our model · NBA document-level test | Style BLEU: 15.87 -> 35.02 | Improved |
| Use interactive attention to jointly relate records and reference words (ablation) | Our model · NBA document-level test | Content Selection F%: 37.97 -> 39.47 | Improved |
| Use interactive attention to jointly relate records and reference words (ablation) | Our model · Sentence-level text manipulation | Content Fidelity F1%: 76.73 -> 76.84 | No clear effect |
| Use back-translation objective (ablation) | Our model · NBA document-level test | Style BLEU: 32.72 -> 35.02 | Improved |
| Use back-translation objective (ablation) | Our model · NBA document-level test | Content Selection F%: 36.16 -> 39.47 | Improved |
| Use back-translation objective (ablation) | Our model · Sentence-level text manipulation | Content Fidelity F1%: 75.56 -> 76.84 | No clear effect |
| Use a hierarchical record encoder instead of a standard MLP-based encoder | Data-to-text generation · NBA document-level test | Content Fidelity # | Improved |
| Use a reference-guided neural generator instead of direct supervised data-to-text generation | Document-scale text manipulation · NBA document-level test | Style BLEU: 35.02 vs 17.43 | Improved |
Closest papers by meaning
- Cognitive Enhancement Chain-of-Thought Towards Enhancing Style Learning and Content Preservation for Long Style Transfer (AAAI 2026 · similarity 0.85)
- Style Transfer in Text: Exploration and Evaluation (AAAI 2018 · similarity 0.84)
- SAIL: Sample-Centric In-Context Learning for Document Information Extraction (AAAI 2025 · similarity 0.82)
- Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection (AAAI 2025 · similarity 0.82)
- BBScore: A Brownian Bridge Based Metric for Assessing Text Coherence (AAAI 2024 · similarity 0.81)
- ParaGuide: Guided Diffusion Paraphrasers for Plug-and-Play Textual Style Transfer (AAAI 2024 · similarity 0.81)
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.
