chinese-word2vec
chinese-word2vec copied to clipboard
Published
20 hours ago •
to-shimo
to-shimo
word2vec/glove/swivel binary file on chinese corpus
chinese-word2vec
word2vec/glove/swivel binary file on chinese corpus
word2vec: https://code.google.com/p/word2vec/
glove: http://nlp.stanford.edu/projects/glove/ swivel: https://github.com/tensorflow/models/tree/master/swivel http://arxiv.org/abs/1602.02215训练语料：百科网页+多个分类新闻语料(全半角转换后)
binary file: （Word2vec的二进制读取可以参考其代码）
word2vec CBOW: utf8 2.18G http://pan.baidu.com/s/1qX334vE word2vec SKIP: utf8 2.17G http://pan.baidu.com/s/1bogTzfp word2vec CBOW: gb18030（精简语料） 2.31G http://pan.baidu.com/s/1jHumqjW word2vec SKIP: gb18030（精简语料） 1.47G http://pan.baidu.com/s/1ntVJBYD swivel: utf8 待上传 glove: utf8 9.19G http://pan.baidu.com/s/1i3XowWP其他：
使用1.25亿英国twitter训练的词向量： 参考地址：https://figshare.com/articles/UK_Twitter_word_embeddings/4052331 下载：https://ndownloader.figshare.com/articles/4052331/versions/1
to-shimo