Hi!
It looks like this project is not complete, right? For example, some codes related to "Embedding Extraction Ablation" in the paper are not mentioned. In the code of your previous work "Robust knowledge graph completion with stacked convolutions and a student re-ranking network", there is no relevant code too.
could you please share the relevant code? Thank you very much.
Or can you explain what does “layers” mean in “We mean pool across all tokens and layers” from your paper? Is it the "last_hidden_state" value of the BERT model outputs?
Hi! It looks like this project is not complete, right? For example, some codes related to "Embedding Extraction Ablation" in the paper are not mentioned. In the code of your previous work "Robust knowledge graph completion with stacked convolutions and a student re-ranking network", there is no relevant code too.
could you please share the relevant code? Thank you very much.