文献阅读-GloVE: Global Vectors for Word Representation

GloVe: Global Vectors for Word Representation

J. Pennington, R. Socher, C. D. Manning, GloVe: Global Vectors for Word Representation, EMNLP (2014)

摘要

当前的单词向量空间表示学习方法（learning vector space representations of words）通过向量运算（vector arithmetic）来捕捉精细的语义与语法规律（fine-grained semantic and syntactic regularities），然而这些规律的可解释性仍然较为薄弱（these regularities has remained opaque）。

本研究对能够生成融合语义与语法特征词向量模型所需具备的特性进行了深入探讨（analyze and make explicit the model properties needed for such regularities to emer