Yoyo

I guess author just wanted to get embedding from train.py instead of considering TransE as a baseline model.

> 非常感谢您的分享，在学习您项目过程中我有一个疑问， FB15K 训练数据的其中一条(随便取的一条)是这样的: /m/027rn /m/06cx9 /location/country/form_of_government 我想问的是这种形式是不是代表　头实体　尾实体　关系　的意思？ 那么最后的关系　 /location/country/form_of_government　该怎么理解，每个 / 后面的内容分别代表什么意思？ 这个问题困扰了我很久，很难找到什么资料，谢谢了！ 我觉得/location/country/form_of_government可以理解为relation的类别1/类别2/relation

Same question here

> I found OpenKE-PyTorch here https://github.com/thunlp/OpenKE/commit/37786b83bb4d4e5ea1ac27ef0de43a8db243e233 But I'm not 100% sure it's OpenKE-PyTorch cause it is not shown on their GitHub homepage.

我觉得要用entity2id和relation2id。因为是对所有entity和relation做embedding.

> But in https://github.com/xwhan/One-shot-Relational-Learning , they didn't release related code to generate these files like rel2candidates.json. :(