Research map / Graph learning / Graph self-supervised learning
A Boundary Token Graph for Zero-Shot Relation Triplet Extraction Involving Discontinuous Entities
Kailun Lyu, Zehan Li, Fu Zhang, Jingwei Cheng
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 |
|---|---|---|---|
| add Boundary Token-Aware Prompts instead of plain relation labels (ablation) | BoG · FewRel multi triplets (m=15) | F1: 25.44 -> 38.24 | Improved |
| add Boundary Token Markers (ablation) | BoG · FewRel multi triplets (m=15) | F1: 21.40 -> 38.24 | Improved |
| add Span-Intra Edges (ablation) | BoG · FewRel multi triplets (m=15) | F1: 24.20 -> 38.24 | Improved |
| add Span-Inter Edges (ablation) | BoG · Disc-FewRel multi triplets (m=15) | F1: 27.54 -> 35.71 | Improved |
| add Span-Inter Edges (ablation) | BoG · FewRel multi triplets (m=15) | F1: 35.57 -> 38.24 | Improved |
| use BoG instead of best baseline on discontinuous-entity data | ZSRTE methods · Disc-Wiki-ZSL multi triplets (m=15) | F1: 22.90 -> 36.70 | Improved |
| use BoG instead of Re-Cent on Wiki-ZSL multi triplets m=5 | ZSRTE methods · Wiki-ZSL multi triplets (m=5) | F1: 55.66 -> 50.16 | Hurt |
| apply BoG to fully supervised discontinuous NER | BoG · ShARe 14 | F1: 81.75 -> 81.28 | No clear effect |
Closest papers by meaning
- OneRel: Joint Entity and Relation Extraction with One Module in One Step (AAAI 2022 · similarity 0.89)
- An Autoregressive Text-to-Graph Framework for Joint Entity and Relation Extraction (AAAI 2024 · similarity 0.87)
- Well-Written Knowledge Graphs: Most Effective RDF Syntaxes for Triple Linearization in End-to-End Extraction of Relations from Texts (Student Abstract) (AAAI 2024 · similarity 0.87)
- Knowledge Graph Completion with Relation-Aware Anchor Enhancement (AAAI 2025 · similarity 0.86)
- COMM: Concentrated Margin Maximization for Robust Document-Level Relation Extraction (AAAI 2025 · similarity 0.86)
- Synergistic Anchored Contrastive Pre-training for Few-Shot Relation Extraction (AAAI 2024 · similarity 0.85)
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.
