Research map / Label-efficient and robust learning / Recognition and long-tail
Joint Word Representation Learning Using a Corpus and a Semantic Lexicon
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 |
|---|---|---|---|
| add synonym-relation regularizer from WordNet (ablation) | Joint GloVe+lexicon · RG | Spearman: 0.7523 -> 0.7866 | Helped |
| add synonym-relation regularizer from WordNet (ablation) | Joint GloVe+lexicon · MEN | Spearman: 0.6933 -> 0.7090 | Helped |
| add synonym-relation regularizer from WordNet (ablation) | Joint GloVe+lexicon · Google syn | accuracy: 66.00 -> 69.33 | Helped |
| add synonym-relation regularizer from WordNet (ablation) | Joint GloVe+lexicon · RW | Spearman: 0.2708 -> 0.2731 | No clear effect |
| add synonym-relation regularizer from WordNet (ablation) | Joint GloVe+lexicon · Google sem | accuracy: 61.49 -> 61.46 | No clear effect |
| add part-meronym relation instead of synonyms (ablation) | Joint GloVe+lexicon · RW | Spearman: 0.2708 -> 0.2761 | Helped |
| add hypernym relation (ablation) | Joint GloVe+lexicon · RW | Spearman: 0.2708 -> 0.2638 | Hurt |
| add hypernym relation (ablation) | Joint GloVe+lexicon · SCWS | Spearman: 0.460 -> 0.4554 | Hurt |
| joint learning instead of retrofitting post-processing | GloVe + synonyms · MEN | Spearman: 0.673 -> 0.709 | Helped |
| joint learning instead of retrofitting post-processing | GloVe + synonyms · RG | Spearman: 0.786 -> 0.787 | No clear effect |
| add synonym regularizer with 10% small corpus (ablation) | Joint GloVe+lexicon · MEN | Spearman | Helped |
| increase dimensionality beyond 300 (ablation) | Joint GloVe+lexicon · RG, MC, MEN | Spearman | No clear effect |
Closest papers by meaning
- Leveraging Web Semantic Knowledge in Word Representation Learning (AAAI 2019 · similarity 0.90)
- Single or Multiple? Combining Word Representations Independently Learned from Text and WordNet (AAAI 2016 · similarity 0.90)
- Semantic Structure-Based Word Embedding by Incorporating Concept Convergence and Word Divergence (AAAI 2018 · similarity 0.89)
- Learning Semantic Representations for Novel Words: Leveraging Both Form and Context (AAAI 2019 · similarity 0.88)
- Learning Context-Specific Word/Character Embeddings (AAAI 2017 · similarity 0.88)
- On the Emergence of Linear Analogies in Word Embeddings (NeurIPS 2025 · similarity 0.88)
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.