Research Area:  Machine Learning
Contextual embeddings, such as ELMo and BERT, move beyond global word representations like Word2Vec and achieve ground-breaking performance on a wide range of natural language processing tasks. Contextual embeddings assign each word a representation based on its context, thereby capturing uses of words across varied contexts and encoding knowledge that transfers across languages. In this survey, we review existing contextual embedding models, cross-lingual polyglot pre-training, the application of contextual embeddings in downstream tasks, model compression, and model analyses.
Author(s) Name:  Qi Liu, Matt J. Kusner, Phil Blunsom
Journal name:  Computer Science
Publisher name:  arXiv:2003.07278
Paper Link:   https://arxiv.org/abs/2003.07278