Glossary term
Glossary term
Foundations
Representing each word in a word set within an embedding vector; that is, representing each word as a vector of floating-point values between 0.0 and 1.0. Words with similar meanings have more-similar representations than words with different meanings. For example, carrots, celery, and cucumbers would all have relatively similar representations, which would be very different from the representations of airplane, sunglasses, and toothpaste.
Created for this library
An NLP team uses word embeddings as input features for a downstream classifier on customer feedback.
A search-quality team uses word embeddings as one signal for query understanding alongside more recent encoder models.
A research team uses word embeddings as a baseline for semantic similarity tasks before evaluating contextualized embeddings.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License