// ⬡ Deep Learning Foundations
GloVe
Word vectors trained on global word co-occurrence counts; Word2Vec’s main peer.
GloVe 词向量 2014 Beginner extended
IN PLAIN WORDS
First count how often every pair of words co-occurs in the corpus, then fit vectors whose dot product approximates the log count. It blends count-based and prediction-based methods, and its vectors support the same “king − man + woman ≈ queen” analogies.
Used in: Pre-trained word-vector baselines, NLP teaching
01Original paper
GloVe: Global Vectors for Word Representation
Jeffrey Pennington, Richard Socher, Christopher Manning · EMNLP 2014 · 2014
DOI ↗ ✓ Verified · Crossref API doi:10.3115/v1/D14-1162
02Where it sits
Learn the left column first; the right column builds on this one.
Related:ELMo (Contextual Word Embeddings)
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
04Where the course teaches it
For AI / data
- Verification: verified, checked 2026-10-22.
- JSON: /api/learn/algorithms.json (id:
glove)