Research map / Label-efficient and robust learning / Recognition and long-tail
A Novel Retrieve-Read-Group Paradigm for Open Knowledge Base Canonicalization
Binhan Yang, Wei Shen, Han Tian
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 relational-view encoder (ablation) | DUVK · ReVerb45K | Average F1: 0.791 -> 0.813 | Improved |
| add relational-view encoder (ablation) | DUVK · OPIEC59K | Average F1: 0.746 -> 0.800 | Improved |
| add semantic-view encoder (ablation) | DUVK · ReVerb45K | Average F1: 0.803 -> 0.813 | Improved |
| add semantic-view encoder (ablation) | DUVK · OPIEC59K | Average F1: 0.754 -> 0.800 | Improved |
| add dual-view cross-training (ablation) | DUVK · ReVerb45K | Average F1: 0.808 -> 0.813 | Improved |
| add dual-view cross-training (ablation) | DUVK · OPIEC59K | Average F1: 0.773 -> 0.800 | Improved |
| add BERT cross-encoder reader stage (ablation) | DUVK · ReVerb45K | Average F1: 0.769 -> 0.813 | Improved |
| add BERT cross-encoder reader stage (ablation) | DUVK · OPIEC59K | Average F1: 0.748 -> 0.800 | Improved |
| use retrieve-read-group instead of embedding-centered HAC pipeline (ablation) | DUVK · ReVerb45K | Average F1: 0.762 -> 0.813 | Improved |
| use retrieve-read-group instead of embedding-centered HAC pipeline (ablation) | DUVK · OPIEC59K | Average F1: 0.731 -> 0.800 | Improved |
| DUVK without external resources versus resource-dependent CLUE | DUVK · ReVerb45K | Average F1: 0.807 -> 0.813 | Improved |
| DUVK without external resources versus resource-dependent CLUE | DUVK · OPIEC59K | Average F1: 0.779 -> 0.800 | Improved |
Closest papers by meaning
- UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition (ICLR 2024 · similarity 0.84)
- SeqGPT: An Out-of-the-Box Large Language Model for Open Domain Sequence Understanding (AAAI 2024 · similarity 0.84)
- Semantic-KG: Using Knowledge Graphs to Construct Benchmarks for Measuring Semantic Similarity (NeurIPS 2025 · similarity 0.83)
- Select and Augment: Enhanced Dense Retrieval Knowledge Graph Augmentation (Abstract Reprint) (AAAI 2024 · similarity 0.83)
- KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledge (NeurIPS 2024 · similarity 0.83)
- MKGL: Mastery of a Three-Word Language (NeurIPS 2024 · similarity 0.83)
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.
