ToneLi
ToneLi
Dear author, I have a question, in metaQA, I have read your code, you used hop1 data to train a hop1 model, hop2 data to train a hop2 model, hop3...
I still get 0.49 in metaQA full KG-hop3. can you provided the whole project (KG embedding, command), or other advice? 0.49 is too low, I do not know what's wrong...
I found your websqp kg embedding file is None, can you supply it? When I run your training embedding code with your KG (relevant your websqp ) . I found...

 Can you supply this file?
can you provide training script of Res14
Hi , Could you help us to check why the answer id in Amazon is not the the provided amazon KG file? for example, answer id 16.  thanks!