Xiao Huang

You should make sure that, you either run on GPU and put all the data on GPU, or run on CPU and put all the data on CPU.

You need to finish the training before performing testing. Wait the training as follows to finish. python3.6 train_detection.py --entity_detection_mode LSTM --fix_embed --gpu 0 python3.6 train_entity.py --qa_mode GRU --fix_embed --gpu 0...

You will need to create training questions and related knowledge graph from the custom document. Thanks.

Thanks for your interest. There must be some issues in your code. I would suggest you to rerun everything from the beginning. Do not change the order of the codes...

#2 There is an issue with the attention model. I didn't get time to fix it. Please refer to #2 for more details. Thanks.

Thanks for your interest. I just checked. The dropbox links are still active. Please make sure that you have access to dropbox. Thanks.

Thank you so much for the comments. Knowledge graph embedding is not the focus of our paper. For the TransE embedding, we directly use the implementation from https://github.com/ZichaoHuang/TransE. I cannot...

Thanks for your interest. Did you make the "Indices" in your evaluation be consistent with the one in the embedding learning? Thanks.

CombG = G[Group1+Group2, :][:, Group1+Group2] The order in the Embedding.mat follows the "Group1+Group2". It is for evaluation. Sorry for the confusion. I just directly release the code in my evaluation....

Yes. CombG = G[Group1+Group2, :][:, Group1+Group2] We use the whole network to train Embedding.mat. After getting Embedding.mat, you could do cross validation on it. Thanks.