What are Embeddings In Machine Learning?


Embeddings are low-dimensional, dense, vector representations of data with the notion of distance which captures the topology of the dataset within the distance structure. Distances between embedding vectors capture similarity between different datapoints, and can capture essential concepts in the original input.


In natural language processing (see definition of ‘natural language processing), embedding is a term used for the representation of words for text analysis, typically in the form of a real-valued vector that encodes the meaning of the word such that the words that are closer in the vector space are expected to be similar in meaning.

Embedding graphic

Sign up for our monthly newsletter, The Drift.