AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Triple Classification Using Regions and Fine-Grained Entity Typing

Tiansi Dong, Zhigang Wang, Juanzi Li, Christian Bauckhage, Armin B. Cremers

AAAI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 30 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
increase radius ratio gamma (ablation)n-ball triple classification · WN11-nballprecision vs recallMixed
longer fine-grained type chains (ablation)n-ball triple classification with TEKE embeddings · WN11-nballprecision: above 90% when chain length greater than 2Improved
use TEKE embeddings (KG plus corpus) instead of TransE (ablation)n-ball triple classification · WN11-nball, WN18-nballaccuracy stabilityImproved
n-ball model vs reported TEKE resulttriple classification · WN11accuracy: 75.9% -> 73%Hurt
n-ball model vs reported TEKE resulttriple classification · FB13accuracy: 77.4% -> 78%No clear effect

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