Research map / Large language models / Language, safety and interpretability
Title-Guided Encoding for Keyphrase Generation
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 title-guided encoding (ablation) | TG-Net · Krapivin present keyphrase prediction | F1@5: 0.334 -> 0.349 | Helped |
| Add title-guided encoding (ablation) | TG-Net · Krapivin absent keyphrase prediction | R@10: 0.142 -> 0.146 | Helped |
| Add copy mechanism (ablation) | TG-Net · Krapivin present keyphrase prediction | F1@5: 0.306 -> 0.349 | Helped |
| Add copy mechanism (ablation) | TG-Net · Krapivin absent keyphrase prediction | R@10: 0.127 -> 0.146 | Helped |
| Use title-guided encoding rather than treating title and body as one undifferentiated source | TG-Net · Inspec present keyphrase prediction | F1@10: 0.346 -> 0.381 | Helped |
| Use title-guided encoding rather than treating title and body as one undifferentiated source | TG-Net · KP20k absent keyphrase prediction | R@50: 0.225 -> 0.268 | Helped |
| Apply title-guided encoding instead of CopyRNN | TG-Net · KP20k present keyphrase prediction | F1@10: 0.262 -> 0.315 | Helped |
| Apply title-guided encoding | TG-Net versus CopyRNN · KP20k documents with title length ratios below 3% and above 12% | F1@5 | Helped |
Closest papers by meaning
- Unsupervised Deep Keyphrase Generation (AAAI 2022 · similarity 0.88)
- Fast and Constrained Absent Keyphrase Generation by Prompt-Based Learning (AAAI 2022 · similarity 0.85)
- A new dataset for multilingual keyphrase generation (NeurIPS 2022 · similarity 0.85)
- Incorporating Expert Knowledge into Keyphrase Extraction (AAAI 2017 · similarity 0.85)
- Retrieval is Accurate Generation (ICLR 2024 · similarity 0.81)
- LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs (ICLR 2025 · 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.