search

zjunlp / MKGformer

[SIGIR 2022] Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion
MIT License
168 stars 28 forks source link

Link predict in MKG task #1

Closed liang-ry closed 2 years ago

liang-ry commented 2 years ago

Is it possible to predict tail entity T (h,r,?) only from the head entity H and relation R in MKG task? Is it possible to perform (? ,r,t) link prediction task? Since I did not see the specific description of the prediction header entity in detail in the paper, I really hope you can answer. Thank you!

njcx-ai commented 2 years ago

Thanks for your attention!

  1. I understand that you are asking whether our model can predict tail entity T (h,r,?) only from the head entity H and relation R without pictures. If so, you can cut off the VIT model and only leverage the BERT-like model to conduct conventional link prediction tasks.
  2. The experiments on link prediction tasks include (?, r, t) and (h, r, ?) , we just take (h, r, ?) as example in the paper. You can refer to the detailed operation in our code.