Efficient Estimation of Word Representations in Vector Space
arXiv： 1301.3781
TLDR（中文）
Word2Vec 提出了词向量（词嵌入）的概念：通过在大规模文本上训练神经网络，让语义相近的词 在向量空间中距离相近。"king - man + woman ≈ queen"的类比关系让世人看到了词嵌入的威力， 为后来所有语言模型的嵌入层奠定了基础。
TLDR (English)
Word2Vec introduced the concept of word embeddings: training neural networks on large text corpora so semantically similar words cluster in vector space. The famous "king - man + woman ≈ queen" analogy demonstrated its power, laying the foundation for embedding layers in all subsequent language models.