Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

8.2——NLP相关了解(四) #17

Open
li-aolong opened this issue Aug 5, 2019 · 0 comments
Open

8.2——NLP相关了解(四) #17

li-aolong opened this issue Aug 5, 2019 · 0 comments
Labels
NLP 自然语言处理(Natural Language Processing)

Comments

@li-aolong
Copy link
Owner

Word Vector

  • one-hot
  • Word2Vec(direct prediciton模型)
    • 优点:可以概括比相关性更为复杂的信息,进行word analogy等任务时效果较好
    • 缺点:对统计信息利用的不够充
    • 实现算法:Skip-Gram model算法;Continuous Bag of Words(CBOW)
  • SVD(count based模型)
    • 优点:训练快速,有效利用了统计信息
    • 缺点:对高频词汇较为偏向;仅能概括词组的相关性;对解释词的含义等任务效果不好
  • GloVe算法
    • 融合了矩阵分解Latent Semantic Analysis (LSA)的全局统计信息和local context window优势,融入全局的先验统计信息,可以加快模型的训练速度,又可以控制词的相对权重。
@li-aolong li-aolong added the NLP 自然语言处理(Natural Language Processing) label Aug 5, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
NLP 自然语言处理(Natural Language Processing)
Projects
None yet
Development

No branches or pull requests

1 participant