Variational Knowledge Graph Reasoning – 第2页 – NLPIR自然语言处理与信息检索共享平台

自然语言处理与信息检索共享平台 自然语言处理与信息检索共享平台

Variational Knowledge Graph Reasoning


Last Monday, Qinghong Jiang gave a presentation about the paper, Variational Knowledge Graph Reasoning, and shared some opinion on it.

This paper proposed to combine these two steps – “Path-Finding” and “Path-
Reasoning” – together as a whole from the perspective of the latent variable graphic model. This graphic model views the paths as discrete latent variables and relation as the observed variables with a given entity pair as the condition, thus the path-finding module can be viewed as a prior distribution to infer the underlying links in the KG. In contrast, the path reasoning module can be viewed as the likelihood distribution, which classifies underlying links into multiple classes.

The authors explained why is the results on the NELL dataset much smaller than results on the FB15k dataset, because NELL is a simple dataset, but FB15k is much harder than NELL and arguably more relevant for real-world scenarios.

You May Also Like

About the Author: nlpvv