hop1 results in metaQA about embedkgqa HOT 3 CLOSED

That command is for half kg, for full you need to replace --kg_type half with --kg_type full in the command.

python3 main.py --mode train --relation_dim 200 --hidden_dim 256
--gpu 2 --freeze 0 --batch_size 128 --validate_every 5 --hops 2 --lr 0.0005 --entdrop 0.1 --reldrop 0.2 --scoredrop 0.2
--decay 1.0 --model ComplEx --patience 5 --ls 0.0 --kg_type half

We found that using BiLSTM is good enough when we have a large number of questions as in MetaQA and saves a lot of training time and compute without affecting the results - you should get the same results with the fixed command.

from embedkgqa.

Thanks, the commond in hop1, hop2 and hop3 is same? just the parameters "hops" is different? On the other hand, can you supply the half metaQA training command? to get the entity embedding and relation embedding?

from embedkgqa.

Thanks, the commond in hop1, hop2 and hop3 is same? just the parameters "hops" is different

Yes

can you supply the half metaQA training command? to get the entity embedding and relation embedding?

Sure, please create this as another issue so it is easier to track, thanks!

from embedkgqa.