search

JunhengH / joie-kdd19

Code and dataset for paper "Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Concepts" published in KDD'2019.
MIT License
82 stars 16 forks source link

Instructions for running the model #4

Open liu-jc opened 4 years ago

liu-jc commented 4 years ago

Could you provide more detailed instructions for running the model? Thank you!

liu-jc commented 4 years ago

And also how to reproduce the results in the paper?

ZihengZZH commented 4 years ago

Could you provide more detailed instructions for running the model? Thank you! python training_model2_scai2.py --kg1f ./dbpedia/db_insnet_train.txt --kg2f ./dbpedia/db_onto_small_mini.txt --modelname ./models --method transe --bridge CMP-linear --alignf ./dbpedia/db_InsType_mini.txt

liu-jc commented 4 years ago

Could you provide more detailed instructions for running the model? Thank you! python training_model2_scai2.py --kg1f ./dbpedia/db_insnet_train.txt --kg2f ./dbpedia/db_onto_small_mini.txt --modelname ./models --method transe --bridge CMP-linear --alignf ./dbpedia/db_InsType_mini.txt

Thanks for your reply. I tried it and conducted the evaluation on the test set. On dbpedia test set, I got HITS@10 around 0.20 on instance view and 0.80 on ontology view. The performance on instance view is quite bad. May I know whether you could get the similar results with those in the paper?

gutihernandez commented 3 years ago

@liu-jc How did you manage to evaluate the model? Evaluation script does not exist at all...

liu-jc commented 3 years ago

@liu-jc How did you manage to evaluate the model? Evaluation script does not exist at all...

I implemented the evaluation by myself. You can try to implement and see whether you can get the reported performance.

Muskan-R-S commented 3 months ago

@liu-jc Can you please share the evaluation script?