AI engineering glossary · NLP embeddings
What is ELMo?
ELMo (also called Embeddings from Language Models): A contextual embedding method that computes word vectors from the internal states of a bidirectional LSTM language model trained on large text. Its word representations change with the sentence, and it was an early step towards pretrained language models.
ELMo: an example
ELMo gives "play" different vectors in "a play at the theatre" and "children play cricket".
Related terms
- Contextual embedding
- Static embedding
- Language model
More NLP embeddings terms
- Entity linking
- Entity-level F1
- FastText
- Fuzzy matching
- Gazetteer
- GloVe
- Hard negative mining
- Hidden Markov model
Where you learn it
ELMo is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.