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