Research map / Label-efficient and robust learning / Recognition and long-tail
Making the Relation Matters: Relation of Relation Learning Network for Sentence Semantic Matching
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| use R²-Net instead of BERT-base | sentence semantic matching · SNLI Full test | accuracy: 90.3% -> 91.1% | Helped |
| use R²-Net instead of BERT-base | sentence semantic matching · SNLI Hard test | accuracy: 80.8% -> 81.0% | Helped |
| use R²-Net instead of BERT-base | sentence semantic matching · SICK test | accuracy: 88.5% -> 89.2% | Helped |
| use R²-Net instead of BERT-base | sentence semantic matching · SciTail test | accuracy: 92.0% -> 92.9% | Helped |
| use R²-Net instead of BERT-base | sentence semantic matching · Quora test | accuracy: 91.0% -> 91.6% | Helped |
| use R²-Net instead of BERT-base | sentence semantic matching · MSRP test | accuracy: 84.2% -> 84.3% | Helped |
| add the local encoder (ablation) | R²-Net · SNLI test | accuracy: 90.7% -> 91.1% | Helped |
| add the local encoder (ablation) | R²-Net · SciTail test | accuracy: 92.6% -> 92.9% | Helped |
| add R² task learning (ablation) | R²-Net · SNLI test | accuracy: 90.5% -> 91.1% | Helped |
| add R² task learning (ablation) | R²-Net · SciTail test | accuracy: 92.3% -> 92.9% | Helped |
| add triplet loss (ablation) | R²-Net · SNLI test | accuracy: 90.9% -> 91.1% | Helped |
| add triplet loss (ablation) | R²-Net · SciTail test | accuracy: 92.6% -> 92.9% | Helped |
Closest papers by meaning
- Large Scaled Relation Extraction With Reinforcement Learning (AAAI 2018 · similarity 0.88)
- GDPNet: Refining Latent Multi-View Graph for Relation Extraction (AAAI 2021 · similarity 0.88)
- DRr-Net: Dynamic Re-Read Network for Sentence Semantic Matching (AAAI 2019 · similarity 0.87)
- Are Noisy Sentences Useless for Distant Supervised Relation Extraction? (AAAI 2020 · similarity 0.87)
- Inducing Relational Knowledge from BERT (AAAI 2020 · similarity 0.87)
- Enhancing Low-Resource Relation Representations through Multi-View Decoupling (AAAI 2024 · similarity 0.86)
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.