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
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 triplet contrastive learning to CGT (ablation) | CGT(UniLM) · NYT test | F1: 84.3 -> 89.1 | Improved |
| add triplet contrastive learning to CGT (ablation) | CGT(UniLM) · WebNLG test | F1: 80.8 -> 83.4 | Improved |
| use UniLM initialization instead of random initialization (ablation) | CGT · NYT test | F1: 83.7 -> 89.1 | Improved |
| use UniLM initialization instead of random initialization (ablation) | CGT · WebNLG test | F1: 78.1 -> 83.4 | Improved |
| use UniLM initialization instead of random initialization (ablation) | CGT · MIE test | F1: 68.80 -> 79.42 | Improved |
| use CGT(UniLM) instead of CasRel | triple extraction · NYT test | F1: 89.6 vs 89.1 | Hurt |
| use CGT(UniLM) instead of CasRel | triple extraction · WebNLG test | F1: 91.8 vs 83.4 | Hurt |
| use CGT(UniLM) instead of MIE-multi | triple extraction · MIE test | F1: 66.40 -> 79.42 | Improved |
Closest papers by meaning
- Well-Written Knowledge Graphs: Most Effective RDF Syntaxes for Triple Linearization in End-to-End Extraction of Relations from Texts (Student Abstract) (AAAI 2024 · similarity 0.86)
- DOGR: Leveraging Document-Oriented Contrastive Learning in Generative Retrieval (AAAI 2025 · similarity 0.82)
- Tractable Transformers for Flexible Conditional Generation (ICML 2025 · similarity 0.82)
- GRACE: Generative Representation Learning via Contrastive Policy Optimization (ICLR 2026 · similarity 0.82)
- A Systematic Exploration of Knowledge Graph Alignment with Large Language Models in Retrieval Augmented Generation (AAAI 2025 · similarity 0.82)
- Hybrid Reciprocal Transformer with Triplet Feature Alignment for Scene Graph Generation (CVPR 2025 · 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.
