Research map / Vision-language and multimodal / Human and embodied modeling
Improving Biomedical Entity Linking with Cross-Entity Interaction
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 KB-enhanced synonym MLM pretraining (ablation) | Prompt-BioEL · NCBI disease | Acc@1: 91.5 → 92.6 | Helped |
| Add KB-enhanced synonym MLM pretraining (ablation) | Prompt-BioEL · BC5CDR | Acc@1: 93.0 → 93.7 | Helped |
| Add KB-enhanced synonym MLM pretraining (ablation) | Prompt-BioEL · COMETA | Acc@1: 83.3 → 83.7 | Helped |
| Use cross-entity re-ranking instead of a cross-encoder (ablation) | Prompt-BioEL · NCBI disease | Acc@1: 90.9 → 91.5 | Helped |
| Use cross-entity re-ranking instead of a cross-encoder (ablation) | Prompt-BioEL · BC5CDR | Acc@1: 91.8 → 93.0 | Helped |
| Use cross-entity re-ranking instead of a cross-encoder (ablation) | Prompt-BioEL · COMETA | Acc@1: 83.1 → 83.3 | Helped |
| Keep the natural-language words in the prompt (ablation) | Prompt-BioEL · NCBI disease | Acc@1: 92.0 → 92.6 | Helped |
| Keep the natural-language words in the prompt (ablation) | Prompt-BioEL · BC5CDR | Acc@1: 93.1 → 93.7 | Helped |
| Keep the natural-language words in the prompt (ablation) | Prompt-BioEL · COMETA | Acc@1: 83.7 → 83.7 | No clear effect |
| Keep the question in the prompt (ablation) | Prompt-BioEL · NCBI disease | Acc@1: 92.0 → 92.6 | Helped |
| Keep the question in the prompt (ablation) | Prompt-BioEL · BC5CDR | Acc@1: 93.4 → 93.7 | Helped |
| Keep the question in the prompt (ablation) | Prompt-BioEL · COMETA | Acc@1: 83.4 → 83.7 | Helped |
Closest papers by meaning
- A Lightweight Neural Model for Biomedical Entity Linking (AAAI 2021 · similarity 0.91)
- Simultaneously Linking Entities and Extracting Relations from Biomedical Text without Mention-Level Supervision (AAAI 2020 · similarity 0.89)
- LATTE: Latent Type Modeling for Biomedical Entity Linking (AAAI 2020 · similarity 0.89)
- DocKS-RAG: Optimizing Document-Level Relation Extraction through LLM-Enhanced Hybrid Prompt Tuning (ICML 2025 · similarity 0.83)
- Knowledge Graph Completion with Relation-Aware Anchor Enhancement (AAAI 2025 · similarity 0.82)
- 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.