ELMo

ELMo (Embeddings from Language Models) introduced the idea of deep contextualized word representations. It extends previous ideas like word2vec and GloVe. The ELMo model is a neural network able to map natural language into a vector space.

Guest

ELMo: ELMo (Embeddings from Language Models) is a contextual word-representation method introduced by researchers associated with the Allen Institute for AI. Unlike fixed word embeddings, ELMo generates representations that change according to a word's sentence context.