Research Area:  Machine Learning
This work lists and describes the main recent strategies for building fixed-length, dense and distributed representations for words, based on the distributional hypothesis. These representations are now commonly called word embeddings and, in addition to encoding surprisingly good syntactic and semantic information, have been proven useful as extra features in many downstream NLP tasks.
Author(s) Name:  Felipe Almeida, Geraldo Xexéo
Journal name:  arXiv.org/CS
Publisher name:  arXiv.org
Volume Information:  arXiv:1901.09069
Paper Link:   https://arxiv.org/abs/1901.09069