各种中文词向量集合

中文词向量集合
https://github.com/Embedding/Chinese-Word-Vectors

Word2vec / Skip-Gram with Negative Sampling (SGNS)
CorpusContext Features
WordWord + NgramWord + CharacterWord + Character + Ngram
Baidu Encyclopedia 百度百科300d300d300d300d
Wikipedia_zh 中文维基百科300d300d300d300d
People's Daily News 人民日报300d300d300d300d
Sogou News 搜狗新闻300d300d300d300d
Financial News 金融新闻300d300d300d300d
Zhihu_QA 知乎问答 300d300d300d300d
Weibo 微博300d300d300d300d
Literature 文学作品300d300d300d300d
Complete Library in Four Sections
四库全书*
300d300dNANNAN
Mixed-large 综合
Baidu Netdisk / Google Drive
300d
300d
300d
300d
300d
300d
300d
300d
Positive Pointwise Mutual Information (PPMI)
CorpusContext Features
WordWord + NgramWord + CharacterWord + Character + Ngram
Baidu Encyclopedia 百度百科SparseSparseSparseSparse
Wikipedia_zh 中文维基百科SparseSparseSparseSparse
People's Daily News 人民日报SparseSparseSparseSparse
Sogou News 搜狗新闻SparseSparseSparseSparse
Financial News 金融新闻SparseSparseSparseSparse
Zhihu_QA 知乎问答 SparseSparseSparseSparse
Weibo 微博SparseSparseSparseSparse
Literature 文学作品SparseSparseSparseSparse
Complete Library in Four Sections
四库全书*
SparseSparseNANNAN
Mixed-large 综合SparseSparseSparseSparse

*Character embeddings are provided, since most of Hanzi are words in the archaic Chinese.

  • 0
    点赞
  • 6
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值