Research map / Large language models / Language, safety and interpretability
On the Transitivity of Hypernym-Hyponym Relations in Data-Driven Lexical Taxonomies
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 weighted voting instead of majority voting to aggregate triple predictions (ablation) | transitivity-based pair classifier · Term-pair relation generation | F1: 91.5% -> 93.0% | Helped |
| use voting over triple classifier outputs instead of a pair-level classifier on pooled features (ablation) | transitivity-based pair classifier · Term-pair relation generation | F1: 89.2% -> 91.5% | Helped |
| use random forest instead of SVM/k-NN classifiers | transitivity triple classifier · Transitivity triple classification | F1: 0.8809 -> 0.9221 | Helped |
| use only top 11 chi2-ranked features rather than all (ablation) | random forest · Transitivity triple classification | F1 | No clear effect |
Closest papers by meaning
- ExTaSem! Extending, Taxonomizing and Semantifying Domain Terminologies (AAAI 2016 · similarity 0.88)
- One Homonym per Translation (AAAI 2020 · similarity 0.86)
- Learning Term Embeddings for Lexical Taxonomies (AAAI 2021 · similarity 0.86)
- Improving Hypernymy Prediction via Taxonomy Enhanced Adversarial Learning (AAAI 2019 · similarity 0.86)
- The Geometry of Categorical and Hierarchical Concepts in Large Language Models (ICLR 2025 · similarity 0.82)
- Idiosyncrasies in Large Language Models (ICML 2025 · similarity 0.81)
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.