AI Paper Atlas

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

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Uncertainty-aware multi-view learning · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
add relational-view encoder (ablation)DUVK · ReVerb45KAverage F1: 0.791 -> 0.813Improved
add relational-view encoder (ablation)DUVK · OPIEC59KAverage F1: 0.746 -> 0.800Improved
add semantic-view encoder (ablation)DUVK · ReVerb45KAverage F1: 0.803 -> 0.813Improved
add semantic-view encoder (ablation)DUVK · OPIEC59KAverage F1: 0.754 -> 0.800Improved
add dual-view cross-training (ablation)DUVK · ReVerb45KAverage F1: 0.808 -> 0.813Improved
add dual-view cross-training (ablation)DUVK · OPIEC59KAverage F1: 0.773 -> 0.800Improved
add BERT cross-encoder reader stage (ablation)DUVK · ReVerb45KAverage F1: 0.769 -> 0.813Improved
add BERT cross-encoder reader stage (ablation)DUVK · OPIEC59KAverage F1: 0.748 -> 0.800Improved
use retrieve-read-group instead of embedding-centered HAC pipeline (ablation)DUVK · ReVerb45KAverage F1: 0.762 -> 0.813Improved
use retrieve-read-group instead of embedding-centered HAC pipeline (ablation)DUVK · OPIEC59KAverage F1: 0.731 -> 0.800Improved
DUVK without external resources versus resource-dependent CLUEDUVK · ReVerb45KAverage F1: 0.807 -> 0.813Improved
DUVK without external resources versus resource-dependent CLUEDUVK · OPIEC59KAverage F1: 0.779 -> 0.800Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy