mug2mag
mug2mag
> I also had a try on MetaQA. It seems weird to me because they perform different on the link prediction task, so I thought an embedding with better quality...
@apoorvumang Thanks very much for your quick reply. > The point they make in the paper is that all scoring functions perform roughly the same. The reason that earlier models...
@apoorvumang hi again > Oh got it. Did you do this in the full KG setting? I do this over the full KG setting but also with training set, valid...
@apoorvumang Different results with different split strategies in knowledge embedding learning stage. 1. training set: validation set: test set = 3:1:1  2. training set: validation set: test set =...
@apoorvumang Yes, it's very weird. Specific information about my KG: ``` train: 965250 test: 193050 valid: 193050 The toolkit is importing datasets. The total of relations is 250. The total...
Embedding size is 200
@apoorvumang Thank you very much! I will try your suggestions. if there are some findings, I will let you know. Thanks again.
@shijx12 hi, could you please offer the links of MovieQA and GloVe 300d pretrained vector？It seems that these two links are invalid.
@haozhiqianga @capella12 @jackywu @YuHao-Luo 可以加微信mugtmag，我加您入群