Research map / Architectures and efficiency / RNNs and normalization
A Dataset for Low-Resource Stylized Sequence-to-Sequence Generation
Yu Wu, Yunli Wang, Shujie 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 |
|---|---|---|---|
| end-to-end teacher-student instead of pivot pipeline (Pivotmodel) | stylized S2S on MTFC · MTFC test | BLEU: 38.75 -> 40.07 | Improved |
| back-translation instead of pivot pipeline (Pivotmodel) | stylized S2S on MTFC · MTFC test | BLEU: 38.75 -> 40.68 | Improved |
| back-translation instead of teacher-student | stylized S2S on MTFC · MTFC test | human formality: 0.57 -> 0.46 | Hurt |
| rewrite pivot output with rules (Pivotrule) vs model pivot, human overall (ablation) | pivot-based method · MTFC test | human overall rank score: 2.76 -> 3.14 | Improved |
| teacher-student instead of pivot pipeline | stylized S2S on TCFC · TCFC test | human overall rank score: 3.47 -> 4.10 | Improved |
| back-translation instead of teacher-student | stylized S2S on TCFC · TCFC test | Distinct-1: 0.052 -> 0.113 | Improved |
| back-translation instead of teacher-student | stylized S2S on TCFC · TCFC test | automatic formality: 0.862 -> 0.844 | Hurt |
| longer source sentences | all baselines · MTFC test | BLEU | Hurt |
Closest papers by meaning
- Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines (ICML 2024 · similarity 0.86)
- WildChat-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training (ICML 2025 · similarity 0.85)
- Parameterized Synthetic Text Generation with SimpleStories (NeurIPS 2025 · similarity 0.85)
- Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models (NeurIPS 2024 · similarity 0.83)
- A Statistical Framework for Ranking LLM-based Chatbots (ICLR 2025 · similarity 0.83)
- A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models (ICLR 2024 · 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.
