Closed irfan11111111 closed 1 year ago
Hi. I think the key point is to use the pre-trained relational model and only tune the final layer. Can you try it again?
Thanks for your reply. Does the pre-trained relational model mean your public simmodelckpt? I tried to initialize BERT by simmodelckpt and only tune the final layer. However, the accuracy is still far from the results in the paper. Can you tell me how to get the pre-trained relational model?
Hi, Sure! I will upload the sample code or send to you asap. Btw, can you tell me your email address?
Thank you! My email address is chenyifan@nudt.edu.cn. Hope to hear from you!
Thanks for your excellent work about incremental few-shot relation learning. It is really interesting and insightful. I tried to experiment with BERT, but the accuracy is far from the results in the paper. Are you welling to open how to run CFRE based on BERT? Whether I can get this part of the code. My email address is hanbj890@nenu.edu.cn. Hope to hear from you!
Hi, @qcwthu Thanks for your excellent work about incremental few-shot relation learning. It is really interesting and insightful. I tried to experiment with BERT, but the accuracy is far from the results in the paper. Are you welling to open how to run CFRE based on BERT?