Research Area:  Machine Learning

Abstract:

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.

Keywords:  

Author(s) Name:  Qi Liu, Matt J. Kusner, Phil Blunsom

Publisher name:  arXiv:2003.07278

DOI:  10.48550/arXiv.2003.07278

Volume Information:  

Paper Link:   https://arxiv.org/abs/2003.07278