search

jasmine95dn / kaping_prompt_zero-shot

This contains script that reimplements KAPING framework (Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering, Baek et al. 2023)
15 stars 0 forks source link

Paper reimplementation metrics? #2

Open MihailSalnikov opened 4 months ago

MihailSalnikov commented 4 months ago

Dear author, Thank you for big work for reimplementation paper, I would like to ask you about your results with T* models. Can you share metrics that you achieved by your version? Is it matched with results proposed in paper?

AryaFeng commented 3 months ago

Dear author, Thank you for big work for reimplementation paper, I would like to ask you about your results with T* models. Can you share metrics that you achieved by your version? Is it matched with results proposed in paper?

I don't extract information from the knowledge graph the same way he does. The extracted triplet is in the form of mid. When converting to text, many entity ids cannot be converted to the corresponding name or label. Is it convenient to share your data set (processed)? Wish you a happy life!