Research map / Label-efficient and robust learning / Recognition and long-tail
Fine-Grained Named Entity Typing over Distantly Supervised Data Based on Refined Representations
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 corpus-level graph refinement with edge-weighted attention | FGET-RR · Wiki | macro-F1: 0.812 -> 0.817 (Glove); 0.812 -> 0.847 (contextualized embeddings) | Helped |
| add corpus-level graph refinement with edge-weighted attention | FGET-RR · OntoNotes | micro-F1: 0.652 -> 0.680 (Glove); 0.652 -> 0.685 (contextualized embeddings) | Helped |
| add corpus-level graph refinement with edge-weighted attention | FGET-RR · BBN | macro-F1: 0.743 -> 0.811 (Glove); 0.743 -> 0.819 (contextualized embeddings) | Helped |
| add position features to mention and context encoders (ablation) | FGET-RR Phase-I · Wiki | macro-F1: 0.802 -> 0.807 | Helped |
| add position features to mention and context encoders (ablation) | FGET-RR Phase-I · OntoNotes | macro-F1: 0.690 -> 0.694 | Helped |
| add position features to mention and context encoders (ablation) | FGET-RR Phase-I · BBN | macro-F1: 0.746 -> 0.755 | Helped |
| remove graph refinement (ablation) | FGET-RR · Wiki | macro-F1: 0.817 -> 0.807 | Hurt |
| replace type-based graph with random adjacency (ablation) | FGET-RR · Wiki | macro-F1: 0.817 -> 0.797 | Hurt |
| replace type-based graph with random adjacency (ablation) | FGET-RR · OntoNotes | macro-F1: 0.737 -> 0.641 | Hurt |
| replace type-based graph with random adjacency (ablation) | FGET-RR · BBN | macro-F1: 0.811 -> 0.693 | Hurt |
| use identity adjacency instead of type-based graph (ablation) | FGET-RR · Wiki | macro-F1: 0.817 -> 0.812 | No clear effect |
| use identity adjacency instead of type-based graph (ablation) | FGET-RR · OntoNotes | macro-F1: 0.737 -> 0.681 | Hurt |
Closest papers by meaning
- Improving Neural Fine-Grained Entity Typing With Knowledge Attention (AAAI 2018 · similarity 0.90)
- Seed-Guided Fine-Grained Entity Typing in Science and Engineering Domains (AAAI 2024 · similarity 0.86)
- Multi-Grained Query-Guided Set Prediction Network for Grounded Multimodal Named Entity Recognition (AAAI 2025 · similarity 0.85)
- Span Graph Transformer for Document-Level Named Entity Recognition (AAAI 2024 · similarity 0.85)
- Small Language Model Makes an Effective Long Text Extractor (AAAI 2025 · similarity 0.85)
- Three Heads Are Better than One: Improving Cross-Domain NER with Progressive Decomposed Network (AAAI 2024 · similarity 0.84)
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.