Caglar Demir

I do concur that the subtraction case may seem to be not intitive and it may be subject to the interpretation. However, from my point of view, the substration case...

Yes indeed

We should intergate the following steps into github actions to test TripleStore Using jena-fuseki 1. sudo docker run -p 3030:3030 -e ADMIN_PASSWORD=pw123 stain/jena-fuseki 3. Login http://localhost:3030/#/ with admin and pw123...

Fully agreed with the observation of @namedgraph. We should be able to read an RDF data without enforcing the label information. Is there any update on this @namedgraph @EmanuelCampos ?

Dear @SsnAgo, Thank you for your question. A score of a triple is computed via Eq. 4 as you mentioned. Through Eq. 1 and Eq 5, we previously aimed to...

Firstly, you may want to use [pretrained models provided](https://github.com/dice-group/Convolutional-Complex-Knowledge-Graph-Embeddings#pre-trained-models). If you would like to reproduce experiments, I would suggest you the followings 1. Fix the seed of random number generator...

Yes, it does indeed. At evaluation/inference time, we removed the Conv(.) function to obtain scores of input triples as shown in [here](https://github.com/dice-group/Convolutional-Complex-Knowledge-Graph-Embeddings/blob/8cfb132757e7340cf0a21f863d061c869cee1985/models/complex_models.py#L171). Thereofre, scores are generated solely via the Hermitian...

Lemme know if you face any difficulties

Hello @Jim-Hou You may want to take a look at #7. Therein, I elucidated possible solutions.

[nces_data_generator](https://github.com/dice-group/Ontolearn/tree/master/ontolearn/nces_data_generator) is not a python package or a python module but rather, it is a folder containing two scripts, i.e., 1. https://github.com/dice-group/Ontolearn/blob/master/ontolearn/nces_data_generator/generate_data.py 2. https://github.com/dice-group/Ontolearn/blob/master/ontolearn/nces_data_generator/helper_classes.py Ideally, we should have a python...