Usage:
use official word2vec
TestGensimWord2Vec_Model_pc.py
'Word60.model'
use Chinese w2v from WX
use Chinese w2v from baike
use own-training from wiki
(see below)
Own Train
program
TrainGensimWord2VecWiki.py
input:
enwiki-latest-pages-articles.xml.bz2
Output:
wiki-english_wordids.txt.bz2