Research map / Detection and segmentation / Open-set and few-shot detection
Hypernym Detection Using Strict Partial Order Networks
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 SPON rather than HyperbolicCones | Unsupervised hypernym detection · LEDS | Average Precision: .89 -> .91 | Helped |
| use SPON rather than HyperbolicCones | Unsupervised direction prediction · BLESS | Average Accuracy: .94 -> .97 | Helped |
| use SPON rather than HyperbolicCones | Unsupervised direction prediction · WBLESS | Average Accuracy: .90 -> .91 | Helped |
| use SPON rather than HyperbolicCones | Unsupervised hypernym detection · BLESS | Average Precision: .81 -> .81 | No clear effect |
| use SPON rather than HyperbolicCones | Unsupervised direction prediction · BIBLESS | Average Accuracy: .87 -> .87 | No clear effect |
| use SPON rather than CRIM | SemEval hypernym discovery · Music | MAP: 40.97 -> 54.70 | Helped |
| use SPON rather than CRIM | SemEval hypernym discovery · Medical | MAP: 34.05 -> 33.50 | Hurt |
| add the Residual connection (ablation) | SPON · BLESS | Average Precision: .73 -> .81 | Helped |
| add the Residual connection (ablation) | SPON · EVAL | Average Precision: .49 -> .50 | Helped |
| add the Residual connection (ablation) | SPON · LEDS | Average Precision: .82 -> .91 | Helped |
| add the Residual connection (ablation) | SPON · WBLESS | Average Precision: .96 -> .98 | Helped |
| replace RELU with Tanh while retaining Residual (ablation) | SPON · BLESS | Average Precision: .81 -> .79 | Hurt |
Closest papers by meaning
- A Tensor Decomposition Perspective on Second-order RNNs (ICML 2024 · similarity 0.84)
- Training Neural Networks as Recognizers of Formal Languages (ICLR 2025 · similarity 0.84)
- Skip a Layer or Loop It? Learning Program-of-Layers in LLMs (ICML 2026 · similarity 0.82)
- Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures (ICLR 2025 · similarity 0.82)
- MIR-Bench: Can Your LLM Recognize Complicated Patterns via Many-Shot In-Context Reasoning? (NeurIPS 2025 · similarity 0.82)
- Search for Efficient Large Language Models (NeurIPS 2024 · 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.