Research map / Label-efficient and robust learning / Recognition and long-tail
Antonym-Synonym Classification Based on New Sub-Space Embeddings
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 |
|---|---|---|---|
| Distill pretrained Glove embeddings into synonym and antonym subspaces | Antonym-synonym classification · Adjective | F1: 0.773 -> 0.884 | Helped |
| Distill pretrained Glove embeddings into synonym and antonym subspaces | Antonym-synonym classification · Verb | F1: 0.768 -> 0.891 | Helped |
| Distill pretrained Glove embeddings into synonym and antonym subspaces | Antonym-synonym classification · Noun | F1: 0.817 -> 0.844 | Helped |
| Distill dLCE embeddings into synonym and antonym subspaces | Antonym-synonym classification · Adjective | F1: 0.897 -> 0.928 | Helped |
| Distill dLCE embeddings into synonym and antonym subspaces | Antonym-synonym classification · Verb | F1: 0.845 -> 0.921 | Helped |
| Distill dLCE embeddings into synonym and antonym subspaces | Antonym-synonym classification · Noun | F1: 0.874 -> 0.911 | Helped |
| Use random vectors instead of Glove embeddings (ablation) | Distiller · Adjective | F1: 0.884 -> 0.698 | Hurt |
| Use random vectors instead of Glove embeddings (ablation) | Distiller · Verb | F1: 0.891 -> 0.771 | Hurt |
| Use random vectors instead of Glove embeddings (ablation) | Distiller · Noun | F1: 0.844 -> 0.702 | Hurt |
| Add distributional similarity feature (ablation) | Glove Distiller · Verb | F1: 0.889 -> 0.891 | Helped |
| Add distributional similarity feature (ablation) | Glove Distiller · Adjective | F1: 0.885 -> 0.884 | No clear effect |
| Add negation-prefix feature (ablation) | Glove Distiller · Noun | F1: 0.835 -> 0.844 | Helped |
Closest papers by meaning
- Learning Term Embeddings for Lexical Taxonomies (AAAI 2021 · similarity 0.87)
- Enriching Word Embeddings with a Regressor Instead of Labeled Corpora (AAAI 2019 · similarity 0.86)
- Joint Word Representation Learning Using a Corpus and a Semantic Lexicon (AAAI 2016 · similarity 0.86)
- Inducing Relational Knowledge from BERT (AAAI 2020 · similarity 0.85)
- Semantic Structure-Based Word Embedding by Incorporating Concept Convergence and Word Divergence (AAAI 2018 · similarity 0.85)
- On the Emergence of Linear Analogies in Word Embeddings (NeurIPS 2025 · similarity 0.83)
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.