mosaco comments

Results 3 comments of


                                            mosaco

> 我们已经在修改调试中文版本了，目前使用PKU BASE知识库，预计会在6月份发布一个可用的版本。看source code发现构造图的时候用了一些规则，在中文这不是很适用，期待支持中文的版本供参考！

Hi, I meet the same issue. While trying, I got a 83% acc on dev set. However, when I run SentenceMatchDecoder.py. The dev set only got 65.6% acc.

I found the problem. Just set fix_word_vec = True. If not, u should save the embeddings during ur training.