Word Representation
Zhiyuan Liu, Yankai Lin, Maosong Sun · 2020
Abstract Word representation, aiming to represent a word with a vector, plays an essential role in NLP. In this chapter, we first introduce several typical word representation learning methods, including one-hot representation and distributed representation. After that, we present two widely used evaluation tasks for measuring the quality of word embeddings. Finally, we introduce the recent extensions for word representation learning models.