search

thunlp / SE-WRL-SAT

Revised Version of SAT Model in "Improved Word Representation Learning with Sememes"
MIT License
50 stars 8 forks source link

关于SogouT训练的词向量 #16

Closed shuizhonghaitong closed 4 years ago

shuizhonghaitong commented 4 years ago

您好！请问SogouT的语料，您是Clean-SogouT1.tgz和Clean-SogouT2.tgz都有用到吗？是用gensim的word2vec还是google的word2vec训练的呢？用gensim训练的话编码貌似有些问题。。

Fanchao-Qi commented 4 years ago

是的，都用到了。 你指的是baseline的SG和CBOW么？是用的google的word2vec训练的。