Research map / Label-efficient and robust learning / Recognition and long-tail
Improving Neural Fine-Grained Entity Typing With Knowledge Attention
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 |
|---|---|---|---|
| use mention attention instead of semantic attention | KNET · WIKI-AUTO | micro-F1: 74.91 -> 75.72 | Helped |
| use knowledge attention instead of semantic attention | KNET · WIKI-AUTO | micro-F1: 74.91 -> 76.22 | Helped |
| add entity disambiguation to knowledge attention (ablation) | KNET · WIKI-AUTO | micro-F1: 76.22 -> 77.92 | Helped |
| add entity disambiguation to knowledge attention (ablation) | KNET · WIKI-MAN | micro-F1: 71.67 -> 75.32 | Helped |
| add entity disambiguation to knowledge attention (ablation) | KNET · WIKI-AUTO strict accuracy | accuracy: 45.49 -> 47.20 | Helped |
| use knowledge attention instead of mention attention (ablation) | KNET · WIKI-MAN | micro-F1: 72.08 -> 71.67 | Hurt |
| add disambiguation to knowledge attention on erroneously disambiguated subset (ablation) | KNET · WIKI-AUTO Erroneous subset | micro-F1: 59.42 -> 57.56 | Hurt |
| add disambiguation to knowledge attention on correctly disambiguated subset (ablation) | KNET · WIKI-AUTO Correct subset | micro-F1: 79.83 -> 82.33 | Helped |
| raise disambiguation confidence threshold alpha (ablation) | KA+D · validation set | micro-F1 | Mixed |
Closest papers by meaning
- Seed-Guided Fine-Grained Entity Typing in Science and Engineering Domains (AAAI 2024 · similarity 0.89)
- K-ON: Stacking Knowledge on the Head Layer of Large Language Model (AAAI 2025 · similarity 0.83)
- GuideNER: Annotation Guidelines Are Better than Examples for In-Context Named Entity Recognition (AAAI 2025 · similarity 0.83)
- Small Language Model Makes an Effective Long Text Extractor (AAAI 2025 · similarity 0.83)
- KGGen: Extracting Knowledge Graphs from Plain Text with Language Models (NeurIPS 2025 · similarity 0.83)
- Select and Augment: Enhanced Dense Retrieval Knowledge Graph Augmentation (Abstract Reprint) (AAAI 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.