Word2vec工具的提出正是为了解决上面这个问题 [1]。它将每个词表示成一个定长的向量,并使得这些向量能较好地表达不同词之间的相似和类比关系。Word2vec工具包含了两个模型:跳字模型(skip-gram)[2] 和连续词袋模型(continuous bag of words,简称CBOW)[3]。接下来让我们分别介绍这两个模型以及它们的训练方法。
word2vec [1, 2] 的提出是为了解决上面这个问题。它将每个词表示成一个定长的向量,并使得这些向量能较好地表达不同词之间的相似和类比关系。word2vec里包含了两个模型:跳字模型(skip-gram)[1]和连续词袋模型(continuous bag of words,简称CBOW)[2]。,接下来让我们分别介绍这两个模型以及它们的训练方法。
[1] Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems (pp. 3111-3119).
[2] Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems (pp. 3111-3119).
[2] Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation
of word representations in vector space. arXiv:1301.3781.
[3] Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781.