Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Bayesian Neural Word Embedding
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 Bayesian variational Skip-Gram embeddings instead of SG | Word embeddings · WordSim353 | Spearman rank correlation (x100): 58.6 -> 61.1 | Helped |
| Use Bayesian variational Skip-Gram embeddings instead of SG | Word embeddings · SCWS | Spearman rank correlation (x100): 59.4 -> 59.3 | Hurt |
| Use Bayesian variational Skip-Gram embeddings instead of SG | Word embeddings · Rare Words | Spearman rank correlation (x100): 51.2 -> 52.5 | Helped |
| Use Bayesian variational Skip-Gram embeddings instead of SG | Word embeddings · MEN | Spearman rank correlation (x100): 60.9 -> 61.1 | Helped |
| Use Bayesian variational Skip-Gram embeddings instead of SG | Word embeddings · SimLex999 | Spearman rank correlation (x100): 26.4 -> 27.3 | Helped |
| Use Bayesian variational Skip-Gram embeddings instead of SG | Word analogy model · Word analogy (total) | accuracy (%): 42.5 -> 45.1 | Helped |
| Use Bayesian variational Skip-Gram embeddings instead of SG | Word analogy model · Word analogy question groups | accuracy (%) | Mixed |
Closest papers by meaning
- Dynamic Word Embeddings (ICML 2017 · similarity 0.87)
- A Simple but Tough-to-Beat Baseline for Sentence Embeddings (ICLR 2017 · similarity 0.86)
- Improving Word Embeddings with Convolutional Feature Learning and Subword Information (AAAI 2017 · similarity 0.86)
- Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe (NeurIPS 2024 · similarity 0.85)
- Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models (NeurIPS 2025 · similarity 0.84)
- On the Emergence of Linear Analogies in Word Embeddings (NeurIPS 2025 · similarity 0.84)
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.