How to use the model for free text?

[DevinXZhou]

Hello! You work is amazing. I wonder how to create a pipeline in order to generate a knowledge graph from a full article? Should I exhaustively group up words into triples, and then feed into this model for classification? or if there is any other easier ways?

[yao8839836]

@DevinXZhou

Thank you!

Your idea sounds feasible, The main problem is how to group up words into triples, maybe using Named Entity Recognition to detect entities and treating verbs as relations. KG-BERT can help judge the resulting triples.