Skip to content

NLP面试题里面关于Skip-Gram的部分有错误 #38

Description

@kuchikatouko
  1. Skip-Gram示意图箭头画反了
  2. Skip-Gram的解释说反了。可以改为Skip-Gram:考虑一个包含 k 个连续词的上下文窗口,从窗口中选择一个词作为中心词。模型以该中心词作为输入,尝试预测它周围的上下文词。通过在大规模语料上反复训练,如果两个词经常出现在相似的上下文环境中,它们的词嵌入向量就会逐渐变得相似。

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions