AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Contrastive Triple Extraction with Generative Transformer

Hongbin Ye, Ningyu Zhang, Shumin Deng, Mosha Chen, Chuanqi Tan, Fei Huang, Huajun Chen

AAAI 2021 · Architectures and efficiency › Attention and transformers · approach: Language model pretraining and induction · 129 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 triplet contrastive learning to CGT (ablation)CGT(UniLM) · NYT testF1: 84.3 -> 89.1Improved
add triplet contrastive learning to CGT (ablation)CGT(UniLM) · WebNLG testF1: 80.8 -> 83.4Improved
use UniLM initialization instead of random initialization (ablation)CGT · NYT testF1: 83.7 -> 89.1Improved
use UniLM initialization instead of random initialization (ablation)CGT · WebNLG testF1: 78.1 -> 83.4Improved
use UniLM initialization instead of random initialization (ablation)CGT · MIE testF1: 68.80 -> 79.42Improved
use CGT(UniLM) instead of CasReltriple extraction · NYT testF1: 89.6 vs 89.1Hurt
use CGT(UniLM) instead of CasReltriple extraction · WebNLG testF1: 91.8 vs 83.4Hurt
use CGT(UniLM) instead of MIE-multitriple extraction · MIE testF1: 66.40 -> 79.42Improved

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