> ML_ALGORITHM // GLOBAL-VECTORS-GLOVE_v1.0
Global Vectors for Word Representation (GloVe)
Unsupervised log-bilinear model combining advantages of global matrix factorization and local context window methods for word representation.
Static Word Embeddingsself-supervisedhigh-intrinsiclarge (>100k)
Back to All AlgorithmsComputational Complexity
Training Complexity:O(co-occurrence_nonzero_elements * iterations)
Inference Complexity:O(1) vector lookup
Hardware Profile
CPU Friendly:Yes
Requires GPU:No
Memory Footprint:low
Interpretability & Data
Interpretability Tier:high-intrinsic
Training Data Needs:large (>100k)
Interpretability Assessment
Vector dot products directly approximate logarithms of empirical word co-occurrence frequencies.
Suitable Tasks & Supported Modalities
Suitable Tasks:
feature extractiontoken embedding
Supported Modalities:
text
Implementing Libraries
Foundational Literature
Common Pitfalls & Warnings
- Lacks subword tokenization, causing complete failure on misspelled words or morphological variants