the method of limiting the candidate entities

[JiyaoWei]

Hello, Jiawei

Can you help me understand the method of limiting the candidate entities, in "One-Shot Relational Learning for Knowledge Graphs". Many people cited your paper, but they have not given a specific parameters.

How did you make specific restrictions in your experiment? Can you show your code for generating the candidate set?

Looking forward to your reply!

[JiaweiSheng]

Hi there,

We just adopt candidate entities provided by Xiong et al. [2018] for experimental fairness, which was released in https://github.com/xwhan/One-shot-Relational-Learning : )

As far as I am concerned, the candidate entities are selected according to the tail entity type constrain for each relation. For example, the relation of "locatedIn" has a set of tail entity types, such as "country", "city" and so on. The constrain may be derived from Nell and Wiki meta information. For more specific code please refer to Xiong et al. [2018].

[yoyozz88]

But in https://github.com/xwhan/One-shot-Relational-Learning , they didn't release related code to generate these files like rel2candidates.json. :(