用word2vec训练中文词向量

1 训练数据

1. 搜狐 http://www.sogou.com/labs/resource/ca.php
2. 中文维基 https://dumps.wikimedia.org/zhwiki/latest/

2 预处理

jieba https://github.com/fxsjy/jieba

python -m jieba news.txt > cut_result.txt

3 训练

word2vec https://github.com/svn2github/word2vec

./word2vec -train resultbig.txt -output vectors.bin -cbow 0 -size 200 -window 5 -negative 0 -hs 1 -sample 1e-3 -threads 12 -binary 1

参考资料

1. http://www.cnblogs.com/robert-dlut/p/6586621.html
2. http://www.cnblogs.com/Newsteinwell/p/6034747.html
3. http://www.tuicool.com/articles/RB7fqaB