Techniques & Methods
Semantic Similarity
Semantic similarity quantifies how much two texts share in meaning, regardless of the specific words used. It is computed by comparing their vector embeddings using cosine similarity or other distance metrics. High semantic similarity means the texts convey comparable information.
Applications include duplicate detection, question matching, semantic search, and retrieval in RAG systems. Models trained specifically for semantic similarity (like sentence-transformers) significantly outperform general LLMs for this task.
Authority Links
Related Terms
Techniques & Methods
Word Embedding
Technique representing words as dense vectors that capture semantic similarity.
Model Components
Embeddings
Dense numerical vectors that represent text, images, or other content in a high-dimensional space where semantically similar items are geometrically close — the foundational data structure for semantic search and RAG retrieval.
Techniques & Methods
Semantic Search
Search technology that retrieves results based on the meaning of a query rather than exact keyword matches — using embeddings to represent queries and documents as vectors and finding nearest neighbors in semantic space.
Techniques & Methods
Vector Representation
Encoding words, sentences, or concepts as numerical vectors for AI comparison and retrieval.