Beizhe Hu

> 您好，为什么使用预训练词向量和不使用预训练词向量，会有一些差距，感觉使用词向量的时候bleu会特别低，对于yelp数据集 >  我也遇到了和您相同的问题，而且不仅仅是加上预训练的词向量，不加词向量的bleu指标也和论文中给出的有巨大的差距，不知道您后来是如何解决这个问题的？

Hello, thanks for your contribution. I notice that you didn't change some functions designed to preprocess the english datasets in the data_builder file, and you use the multilingual model to...

Thanks for your reply. I am also trying to transferring this work to another language, and before I see your work, I noticed that, even if I have finished work...

Thanks for your reply, your answer helps me lot! By the way, I wanna ask you a question about the `convert_tokens_to_ids()` function of class `BertTokenizer` in `tokenization.py` file, path src/others....

Thank you very much for your quick reply! I followed your advise and check the master brach, and found that this code was not there. Also, I check other branches...

Yes, I was in the same condition when I try to test my model. Have you solved this problem?