Research map / Label-efficient and robust learning / Self-supervised and contrastive
QuanTaxo: A Quantum Approach to Self-Supervised Taxonomy Expansion
Sahil Mishra, Avi Patni, Niladri Chatterjee, Tanmoy Chakraborty
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 |
|---|---|---|---|
| use complex-valued (amplitude and phase) embeddings instead of real-valued (ablation) | QuanTaxo · SemEval16-Env, SemEval16-Sci, MAG-WIKI-PSY | Acc, MRR, Wu&P | Improved |
| use weighted sum instead of direct sum in the mixture model (ablation) | QuanTaxo Quant-Mix (complex) · SemEval16-Env, SemEval16-Sci, MAG-WIKI-CS | Acc, MRR, Wu&P | Hurt |
| use joint representation instead of concatenation for parent-child scoring (ablation) | QuanTaxo · SemEval16-Env, SemEval16-Sci | Acc, MRR, Wu&P | Improved |
| increase density matrix dimensionality (ablation) | QuanTaxo (complex) · SemEval16-Env, SemEval16-Sci, MAG-WIKI-CS | Acc, MRR, Wu&P | No clear effect |
| use superposition (Quant-Sup) instead of mixture (Quant-Mix) representation (ablation) | QuanTaxo · SemEval16-Sci | Acc: 52.4 -> 57.3 | Improved |
| QuanTaxo Quant-Sup vs best baseline TEMP | taxonomy expansion · SemEval16-Sci | Acc: 43.5 -> 57.3 | Improved |
Closest papers by meaning
- Geometric Constraints for Small Language Models to Understand and Expand Scientific Taxonomies (ICLR 2026 · similarity 0.87)
- Learning Term Embeddings for Lexical Taxonomies (AAAI 2021 · similarity 0.86)
- DNG: Taxonomy Expansion by Exploring the Intrinsic Directed Structure on Non-gaussian Space (AAAI 2023 · similarity 0.85)
- Quantum-inspired Non-homologous Representation Constraint Mechanism for Long-tail Senses of Word Sense Disambiguation (AAAI 2025 · similarity 0.84)
- Quantum Interference Model for Semantic Biases of Glosses in Word Sense Disambiguation (AAAI 2024 · similarity 0.82)
- KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledge (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.
