Research map / Image generation / Autoregressive and latent generation
Data-to-Text Generation with Content Selection and Planning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 content selection and planning to the encoder-decoder (ablation) | ED+CC · RotoWire development | BLEU: 13.31 -> 16.19 | Helped |
| Add content selection and planning to the encoder-decoder (ablation) | ED+CC · RotoWire development | CS recall: 32.71 -> 51.21 | Helped |
| Use content selection without content planning (ablation) | ED+CC · RotoWire development | BLEU: 13.31 -> 13.52 | Helped |
| Use content planning without content selection (ablation) | ED+CC · RotoWire development | BLEU: 13.31 -> 14.45 | Helped |
| Use content planning without content selection (ablation) | ED+CC · RotoWire development | CS precision: 27.96 -> 29.57 | Helped |
| Use content planning without content selection (ablation) | ED+CC · RotoWire development | CO DLD: 15.03 -> 15.84 | Helped |
| Replace conditional copy with joint copy (ablation) | NCP+CC · RotoWire development | BLEU: 16.19 -> 14.92 | Hurt |
| Replace conditional copy with joint copy (ablation) | NCP+CC · RotoWire development | CS recall: 51.21 -> 48.56 | Hurt |
| Use an oracle content plan instead of a predicted plan (ablation) | NCP+CC · RotoWire development | BLEU: 16.19 -> 24.11 | Helped |
| Use the proposed system rather than WS-2017 | NCP+CC · RotoWire test | BLEU: 14.19 -> 16.50 | Helped |
| Use the proposed system rather than WS-2017 | NCP+CC · RotoWire test | CS precision: 29.49 -> 34.18 | Helped |
| Use the proposed system rather than WS-2017 | NCP+CC · RotoWire test | RG precision: 74.80 -> 87.47 | Helped |
Closest papers by meaning
- Sentence Generation for Entity Description with Content-Plan Attention (AAAI 2020 · similarity 0.88)
- Order-Planning Neural Text Generation From Structured Data (AAAI 2018 · similarity 0.88)
- Branch-GAN: Improving Text Generation with (not so) Large Language Models (ICLR 2024 · similarity 0.86)
- Towards Text Generation with Adversarially Learned Neural Outlines (NeurIPS 2018 · similarity 0.85)
- Successor Features for Efficient Multi-Subject Controlled Text Generation (ICML 2024 · similarity 0.84)
- Retrieval is Accurate Generation (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.