Word Embeddings are dense vector representations of words in a continuous vector space where semantically similar words are positioned closer together. They capture semantic relationships and contextual meaning by representing words as numerical vectors rather than discrete symbols.

Key characteristics include:

• Dense Representation: Each word is represented by a vector of typically 100-300 dimensions
• Semantic Similarity: Similar words have similar vector representations
• Mathematical Operations: Vector arithmetic can capture semantic relationships (e.g., king - man + woman ≈ queen)

Popular embedding techniques include:

• Word2Vec: CBOW and Skip-gram models
• GloVe: Global Vectors for Word Representation
• FastText: Subword-based embeddings
• Contextual Embeddings: BERT, ELMo that provide context-dependent representations