WaNePr

> Hi, > Your observation is correct. The attention mechanism in MDREA and MHA-1 is the same. There is an implementation issue in the MDREA model. In particular, a sequence...

> I think the MDREA should perform better than MDRE. Let me share an "attention code" from another repository. The attention function in this code requires an additional argument "batch_seq"...

If no SPARQL queries is provided, how to use this dataset properly ?

i see, but to simulate the execution of sparql query, shouldn't we know the query form, e.g. SELECT, ASK, SELECT DISTINCT etc. ?

I am wondering how to check the correct answer of question if only the variables and predicates are known but not the format. Do you mind if you cound point...

How do you evaluate the result ?

Is it possible to provide the pre-processing files and the evaluation scripts so that we know how to evaluate the result

I do know that the dataset is labelled and assessed by human annotators. My question is , I see that you provided a subset of Freebase (2.2GB zip) for evaluations,...

All EntityMid within the subset can be indexed this way ?

But the 'unpopular Freebase MIDs without labels are not in the FreebaseQA dataset , am i right ?