One-shot-Relational-Learning How is the Pre-trained Nell-One calculated? Do you directly use the transE algorithm to perform the embedded calculation on NELL-One?

How is the Pre-trained Nell-One calculated? Do you directly use the transE algorithm to perform the embedded calculation on NELL-One?

Open EchoJZ opened this issue 2 years ago • 2 comments

How is the Pre-trained Nell-One calculated? Do you directly use the transE algorithm to perform the embedded calculation on NELL-One?

Mar 14 '22 13:03 EchoJZ

Hello, I see that you are also interested in the pre-trained vector, where the vector of ComplEx is in the form of real numbers, but I feel that it is in the form of complex numbers from the paper, I don't know if you understand why? Is it easy to answer?

Mar 31 '22 14:03 zhaojiawen-coding

Hi , I have the same question, I am currently trying to recreate the pre-trained embedding for another dataset. Could you advise how was pre-trained embedding done? I used the base TransE model in OpenKE GitHub code (Discussed in the paper) to produce entity2vec.TransE but the format is not in the form of complexed numbers.

Could you share the code on how was pre-trained embedding produced?

Dec 07 '23 01:12 liuran998

One-shot-Relational-Learning One-shot-Relational-Learning copied to clipboard

How is the Pre-trained Nell-One calculated? Do you directly use the transE algorithm to perform the embedded calculation on NELL-One?

One-shot-Relational-Learning
One-shot-Relational-Learning copied to clipboard