Glossary
What is Embedding?
An embedding is a representation of a text, image or record as a list of numbers (a vector) that captures its meaning. Content with similar meaning gets similar vectors. This lets a semantic search recognise, for example, "notice period" and "time limit for terminating the contract" as related, even though the words differ.
In simple terms
Picture a large map on which every sentence is a dot. Sentences that mean the same thing sit close together, even if they use different words. "The car won't start" sits next to "The engine doesn't turn over", but far from "The offer ends in March". An embedding is a sentence's coordinate on that map, just with hundreds of dimensions instead of two.
In the enterprise
Muster Handels GmbH makes its customer service handbook searchable. Each paragraph is converted into a vector by an embedding model and stored in a vector database. When an agent asks "What do we do if goods arrive broken?", the question is turned into a vector too. The search returns the paragraph "Complaints about transport damage", even though the word "broken" does not appear in it.
Related terms
Sources
- Mikolov et al. (2013): Efficient Estimation of Word Representations in Vector Space (arXiv:1301.3781)
- Reimers & Gurevych (2019): Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks (arXiv:1908.10084)
How we use this: UNID AI Second Brain · The second brain for your company's knowledge
See it working on your own material.
In a 30-minute call we show the products live and work out which use case makes sense for you first. No obligation, in German or English, in Vienna or online.
UNID AI · Leonard-Bernstein-Straße 10 · 1220 Vienna · +43 660 476 30 89